Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14156
    Prev
    Next
    INDEX
    Explanations

    technical texts containing chemical or biological data

    oai_token-act-pair · gemini-2.0-flash

    Carbohydrates and sugars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ifferentiated
    -0.52
     climatisation
    -0.52
     '{@
    -0.49
     kanya
    -0.47
    Geografia
    -0.47
    webElementGuid
    -0.47
     gekennzeichnet
    -0.46
     bancaire
    -0.45
    capi
    -0.43
    inguish
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.68
    Personensuche
    0.65
     Complex
    0.64
    MigrationBuilder
    0.63
    parsedMessage
    0.63
    EndContext
    0.62
    Cuer
    0.60
     disambiguazione
    0.60
    AddHtmlAttribute
    0.59
     complex
    0.59
    Activations Density 1.398%

    No Known Activations