© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6297
    Prev
    Next
    INDEX
    Explanations

    mentions of buildings or cities, combined with relative sizes of things

    oai_token-act-pair · gemini-2.0-flash

    Architecture and landmarks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     autorytatywna
    -0.84
    ThroughAttribute
    -0.68
    VIAF
    -0.68
    تفصیلات
    -0.64
    awtextra
    -0.63
    InputBorder
    -0.63
     Anſ
    -0.63
     disambiguazione
    -0.62
    osoba
    -0.61
     AspNetCore
    -0.60
    POSITIVE LOGITS
     pal
    0.60
     Pal
    0.55
    pal
    0.51
     cat
    0.51
    Pal
    0.48
     Cat
    0.46
    alt
    0.44
    Климат
    0.43
     CAT
    0.43
    GraphicsUnit
    0.43
    Activations Density 2.418%

    No Known Activations