© 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. 13041
    Prev
    Next
    INDEX
    Explanations

    the prefix "Bon" or "bon"

    oai_token-act-pair · gemini-2.0-flash

    Bon

    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
     good
    -0.55
     dobre
    -0.52
    rija
    -0.50
     écou
    -0.49
     buen
    -0.48
    Configure
    -0.47
     sahaja
    -0.47
     Good
    -0.47
     likely
    -0.47
    Good
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.84
     esternos
    0.69
    +#+#
    0.69
    PyExc
    0.65
    Xna
    0.64
    tagHelperRunner
    0.63
    Arbitrage
    0.63
    riwal
    0.63
    исленность
    0.61
     المعيارى
    0.59
    Activations Density 0.430%

    No Known Activations