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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3043
    Prev
    Next
    INDEX
    Explanations

    code comments, plus "In" at the beginning of sentences

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     pinulongan
    -0.94
    MigrationBuilder
    -0.93
    WebElementEntity
    -0.89
     disambiguazione
    -0.88
     lenker
    -0.88
    tagext
    -0.85
     дописавши
    -0.84
     صوتيه
    -0.83
    sizeCache
    -0.83
    Personensuche
    -0.83
    POSITIVE LOGITS
     lèvres
    0.40
     حالی
    0.36
    isle
    0.33
     Hert
    0.33
     en
    0.33
     Ketua
    0.32
    ėjimo
    0.32
     تفاوت
    0.32
    GU
    0.31
    PHA
    0.31
    Activations Density 0.371%

    No Known Activations