© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4898
    Prev
    Next
    INDEX
    Explanations

    proper nouns relating to places, especifically colleges and cities/regions

    oai_token-act-pair · gemini-2.0-flash

    College

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    MessageOf
    -0.63
    <bos>
    -0.56
    ętr
    -0.46
    ’
    -0.45
     bes
    -0.44
    oria
    -0.44
    ёх
    -0.43
    htub
    -0.43
    hical
    -0.42
    -};
    -0.42
    POSITIVE LOGITS
    XmlAccessorType
    0.81
     nakalista
    0.65
    SuppressMessage
    0.63
     îna
    0.61
    PMailer
    0.61
    picable
    0.60
    postsleuth
    0.60
     tramonto
    0.59
    DataAnnotations
    0.57
    ConstraintMaker
    0.57
    Activations Density 0.706%

    No Known Activations