© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    time or event markers and also sentiment indications

    oai_token-act-pair · gemini-2.0-flash

    first-person possessive pronouns

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

    Personal stories and conversations

    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
     ་་
    -0.63
     noqa
    -0.57
     .:
    -0.56
    μη
    -0.55
     meridian
    -0.53
    flink
    -0.53
    ScopeManager
    -0.52
    ftagPool
    -0.52
    its
    -0.52
     يتيمه
    -0.52
    POSITIVE LOGITS
     my
    0.60
     our
    0.54
     a
    0.51
    HomeAsUp
    0.48
     recevrez
    0.48
    Życiorys
    0.47
    šanai
    0.47
     MessageBoxIcon
    0.47
     somebody
    0.47
     someone
    0.47
    Activations Density 5.508%

    No Known Activations