© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1009
    Prev
    Next
    INDEX
    Explanations

    occurrences of possessive words and words indicative of action

    oai_token-act-pair · gemini-2.0-flash

    wishes and intentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     initComponents
    -0.71
    tagHelperRunner
    -0.67
    Portail
    -0.66
    الحياه
    -0.64
    ISupport
    -0.63
     стаття
    -0.60
     بيها
    -0.59
     fopen
    -0.59
    Билгалдахарш
    -0.59
    LookAnd
    -0.58
    POSITIVE LOGITS
     wishes
    0.91
     wish
    0.90
    wish
    0.72
    want
    0.63
     Wish
    0.61
     intention
    0.60
     intent
    0.57
     WISH
    0.57
    Wish
    0.57
     intentions
    0.56
    Activations Density 0.746%

    No Known Activations