© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7777
    Prev
    Next
    INDEX
    Explanations

    HTML header tags

    oai_token-act-pair · gemini-2.0-flash

    <h3>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.20
    <h3>
    -1.02
    ↵↵
    -0.91
    '
    -0.78
    -
    -0.78
    ,
    -0.77
    ’
    -0.77
    </h2>
    -0.75
    ↵↵↵
    -0.72
    <eos>
    -0.72
    POSITIVE LOGITS
    setVerticalGroup
    1.16
     Efq
    1.15
     ControllerBase
    1.08
     auffi
    1.06
     Anſ
    1.05
     myſelf
    1.05
     ainfi
    1.05
    sprzedam
    1.03
    ^(@)
    1.03
    ########.
    1.03
    Activations Density 1.562%

    No Known Activations