© 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. 4678
    Prev
    Next
    INDEX
    Explanations

    common words and punctuation that appear frequently

    oai_token-act-pair · gemini-2.0-flash

    forms of "which"

    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
     Efq
    -0.81
    PreInfinity
    -0.74
     protoimpl
    -0.74
     فريبيس
    -0.71
    iffance
    -0.70
    dafx
    -0.69
    cellona
    -0.69
     StringTokenizer
    -0.68
    <?,
    -0.68
     myſelf
    -0.68
    POSITIVE LOGITS
     which
    3.53
    which
    2.97
     Which
    2.78
    Which
    2.67
     WHICH
    2.63
     laquelle
    1.78
    hich
    1.74
     lequel
    1.59
     cual
    1.58
     cui
    1.58
    Activations Density 7.776%

    No Known Activations