© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11400
    Prev
    Next
    INDEX
    Explanations

    text excerpts from witness testimony in court

    oai_token-act-pair · gemini-2.0-flash

    Evidence

    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
     متعلقه
    -0.74
     estekak
    -0.62
     समीक्षाओं
    -0.59
     estimés
    -0.58
     كومونز
    -0.57
     cherchés
    -0.56
    脚注の使い方
    -0.56
     createSprite
    -0.56
    protoimpl
    -0.52
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
     evidence
    1.20
     Evidence
    1.10
    evidence
    1.06
    Evidence
    1.02
     EVIDENCE
    0.96
     evi
    0.74
     evidences
    0.69
     evidencia
    0.67
    vidence
    0.62
    ScopeManager
    0.61
    Activations Density 2.237%

    No Known Activations