© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    words common in technical documentation about computer filesystems, particularly related to backups, deletion, or file recovery

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    出版年
    -0.54
     Verme
    -0.47
    KommentareTeilen
    -0.47
     guarantees
    -0.46
     FetchType
    -0.45
     getItemId
    -0.45
    tableFuture
    -0.44
     paja
    -0.44
     informée
    -0.43
    脚注の使い方
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.59
    criture
    0.56
    WEBPACK
    0.56
    vede
    0.55
    pośred
    0.52
     nakalista
    0.52
     pasi
    0.51
    rawDesc
    0.51
    HOSTS
    0.51
     strangest
    0.50
    Activations Density 1.906%

    No Known Activations