© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6731
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to travel to different parts of a town or city

    oai_token-act-pair · gemini-2.0-flash

    variants of the word "town"

    np_token-act-pair-logits · gpt-4o-mini

    town

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    makeConstraints
    -0.82
    الإنجليزية
    -0.76
     AssemblyCulture
    -0.73
    SequentialGroup
    -0.70
    BagConstraints
    -0.69
     doInBackground
    -0.68
     HasFactory
    -0.66
    featureID
    -0.64
    RenderAtEndOf
    -0.63
    aarrggbb
    -0.60
    POSITIVE LOGITS
     town
    3.30
     TOWN
    2.47
     Town
    2.47
    Town
    2.34
    town
    2.22
    TOWN
    1.97
     towns
    1.84
    towns
    1.48
     Towns
    1.28
    タウン
    1.13
    Activations Density 1.007%

    No Known Activations