© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14649
    Prev
    Next
    INDEX
    Explanations

    numerical data and words that often appear near numbers

    oai_token-act-pair · gemini-2.0-flash

    technical or code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     BitmapFactory
    -0.67
    StoreMessageInfo
    -0.65
    fastjson
    -0.65
     vPvB
    -0.59
     препратки
    -0.58
    Parcelize
    -0.57
     SIMBAD
    -0.56
     jurídica
    -0.56
    MigrationBuilder
    -0.56
    protoimpl
    -0.55
    POSITIVE LOGITS
    بوابة
    0.56
    UnusedPrivate
    0.53
     оригіналу
    0.48
    RunAsync
    0.47
    udesta
    0.46
    naire
    0.44
    EndContext
    0.43
     محفوظة
    0.43
    ghijklmnop
    0.43
    webElement
    0.42
    Activations Density 4.128%

    No Known Activations