© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12057
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to industrial polymer chemistry, especially processes and materials.

    oai_token-act-pair · 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
    cences
    -0.56
    stdc
    -0.52
    dp
    -0.51
    stateProvider
    -0.50
    zzar
    -0.50
    :✨
    -0.50
    iostream
    -0.49
    Conclusie
    -0.49
    ]={
    -0.49
    にほんブログ村
    -0.48
    POSITIVE LOGITS
     onBind
    0.54
    contentLoaded
    0.49
    httphttps
    0.49
     wym
    0.47
    WillAppear
    0.46
    UBL
    0.44
    遂
    0.44
    তথ্যসূত্র
    0.43
     Exacts
    0.42
     carved
    0.42
    Activations Density 9.567%

    No Known Activations