© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10388
    Prev
    Next
    INDEX
    Explanations

    technical writing with commas and words like help, which, can, increase, or features.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     bringing
    -0.97
     Bringing
    -0.88
     putting
    -0.87
     making
    -0.86
     makes
    -0.84
    Bring
    -0.84
     reducing
    -0.84
    bringing
    -0.84
    makes
    -0.84
     Bring
    -0.83
    POSITIVE LOGITS
    tvguidetime
    0.98
    ]")]
    0.81
    IntoConstraints
    0.72
     متعلقه
    0.71
     فريبيس
    0.70
    XmlAccessType
    0.69
    ípios
    0.67
    eleste
    0.66
    extAlignment
    0.65
    swire
    0.64
    Activations Density 2.626%

    No Known Activations