© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8939
    Prev
    Next
    INDEX
    Explanations

    words related to engineering, electronics, anatomy, technical paperwork and violence

    oai_token-act-pair · gemini-2.0-flash

    endings/extremities/structure

    np_max-act · gemini-2.0-flash

    end

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    IntoConstraints
    -0.90
    aarrggbb
    -0.90
    PerformLayout
    -0.87
     oprot
    -0.76
    argout
    -0.74
     anſ
    -0.73
    <bos>
    -0.73
    RegressionTest
    -0.72
     ſhould
    -0.69
    ѝ
    -0.67
    POSITIVE LOGITS
    PathVariable
    0.49
    ActionTypes
    0.46
    protoimpl
    0.46
     flat
    0.43
    HIB
    0.43
    KommentareTeilen
    0.42
     WALL
    0.42
    ฑ
    0.42
    urbation
    0.42
     Gass
    0.41
    Activations Density 2.073%

    No Known Activations