© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3319
    Prev
    Next
    INDEX
    Explanations

    words and phrases which reference caring for animals

    oai_token-act-pair · gemini-2.0-flash

    board

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ArgsConstructor
    -0.60
     înc
    -0.59
    fillType
    -0.57
     CreateTagHelper
    -0.56
    AutoScaleMode
    -0.55
     estekak
    -0.55
     doInBackground
    -0.55
     بيها
    -0.54
    createStatement
    -0.54
     extré
    -0.54
    POSITIVE LOGITS
     board
    1.37
     Board
    1.13
     BOARD
    1.09
    board
    1.02
     boards
    0.98
    Board
    0.97
    BOARD
    0.90
     Boards
    0.88
     boarding
    0.88
     boarded
    0.85
    Activations Density 1.431%

    No Known Activations