© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 321
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and HTML start tags for the main content

    oai_token-act-pair · gemini-2.0-flash

    Legal and code documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.78
    romas
    -0.61
    RegistryLite
    -0.60
    adaptiveStyles
    -0.57
     كومونز
    -0.57
     cdti
    -0.57
    ModelSerializer
    -0.56
    soort
    -0.55
    ";}
    -0.55
    меч
    -0.54
    POSITIVE LOGITS
    Ecotoxicity
    0.53
    prefixer
    0.53
     selve
    0.51
     eigentlichen
    0.50
    ResumeLayout
    0.46
     själva
    0.46
    orgon
    0.45
     principal
    0.45
    ليق
    0.45
     본
    0.44
    Activations Density 3.475%

    No Known Activations