© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6569
    Prev
    Next
    INDEX
    Explanations

    references to urban areas, especially streets and downtown areas.

    oai_token-act-pair · gemini-2.0-flash

    street

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     EconPapers
    -0.72
     Vikipedi
    -0.65
    Jeografia
    -0.64
    aarrggbb
    -0.63
    NameValuePair
    -0.62
     isComment
    -0.60
    IMPORTED
    -0.60
    FieldBuilder
    -0.59
    enumii
    -0.58
    ьаж
    -0.58
    POSITIVE LOGITS
     street
    1.68
     Street
    1.48
     STREET
    1.41
    street
    1.41
    Street
    1.37
     road
    1.36
     strada
    1.33
     Straße
    1.31
    STREET
    1.30
     streets
    1.27
    Activations Density 1.595%

    No Known Activations