© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3174
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes related to memories and childhood or phrases indicating length of time

    oai_token-act-pair · gemini-2.0-flash

    terms related to nostalgia and memories

    np_token-act-pair-logits · gpt-4o-mini

    memories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remember
    -2.05
     remembers
    -1.95
     recalls
    -1.73
     recall
    -1.73
     remembering
    -1.63
     Remember
    -1.62
    remember
    -1.58
     REMEMBER
    -1.57
    Remember
    -1.53
     recalling
    -1.51
    POSITIVE LOGITS
    Personensuche
    0.93
    FieldBuilder
    0.76
    extAlignment
    0.70
     snippetHide
    0.67
    zzleHttp
    0.65
    IBarButtonItem
    0.64
     consultato
    0.63
    IsMutable
    0.63
    itemBuilder
    0.62
    HideFlags
    0.61
    Activations Density 1.210%

    No Known Activations