© 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. 849
    Prev
    Next
    INDEX
    Explanations

    words that indicate the the writing is technical, helpful, and high in quality

    oai_token-act-pair · gemini-2.0-flash

    Expressions including thanks

    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
     arşivlendi
    -0.59
     <<<
    -0.56
    حياته
    -0.56
     createSlice
    -0.55
    {§
    -0.54
    Спољашње
    -0.54
    ########.
    -0.54
     domo
    -0.52
    期刊论文
    -0.52
     MenuView
    -0.52
    POSITIVE LOGITS
    ânsito
    0.48
    laze
    0.47
    boss
    0.46
    vább
    0.46
    MergeFrom
    0.46
     useSelector
    0.45
    tanleria
    0.45
     boss
    0.44
    Panamoan
    0.43
     bosses
    0.42
    Activations Density 1.467%

    No Known Activations