© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    words related to motivation, intent and success or positive affect

    oai_token-act-pair · gemini-2.0-flash

    action-oriented words

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

    Action/process words

    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
     الحره
    -0.67
    UserScript
    -0.65
     Car
    -0.62
    انيف
    -0.61
    ::_('
    -0.60
    DoubleQuotes
    -0.59
    thys
    -0.59
    __.__
    -0.59
    basti
    -0.57
     MainAxisSize
    -0.57
    POSITIVE LOGITS
     solving
    0.57
     executing
    0.55
     introducing
    0.55
     detecting
    0.54
     describing
    0.54
     explaining
    0.53
     eccell
    0.52
     Containing
    0.52
     exposing
    0.52
     denoting
    0.52
    Activations Density 14.632%

    No Known Activations