© 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. 13054
    Prev
    Next
    INDEX
    Explanations

    formatting artifacts in documents

    oai_token-act-pair · gemini-2.0-flash

    lt

    np_max-act · 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
    <sup>
    -0.40
     faltar
    -0.40
     insuffisamment
    -0.39
     così
    -0.39
    check
    -0.38
    tel
    -0.37
    float
    -0.36
     Hoh
    -0.36
    d
    -0.36
     obo
    -0.36
    POSITIVE LOGITS
     esternos
    1.00
     Majefty
    0.90
     pleaſure
    0.88
     متعلقه
    0.88
     Мексичка
    0.87
     houſe
    0.83
     purpoſe
    0.82
     Reſ
    0.79
     ſever
    0.79
    SPATH
    0.78
    Activations Density 0.037%

    No Known Activations