© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8464
    Prev
    Next
    INDEX
    Explanations

    negations and qualifiers, sometimes following verbs

    oai_token-act-pair · gemini-2.0-flash

    evidence and signs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MigrationBuilder
    -0.61
    出版年
    -0.60
    enumi
    -0.54
    ValueStyle
    -0.53
     ويكيميديا
    -0.52
    LookAnd
    -0.52
     protoimpl
    -0.49
    principalColumn
    -0.48
    васто
    -0.46
    ⓘ
    -0.46
    POSITIVE LOGITS
     evidence
    2.25
     signs
    2.08
    evidence
    1.99
    Evidence
    1.87
     sign
    1.87
     Evidence
    1.85
    Signs
    1.72
     EVIDENCE
    1.70
    signs
    1.70
     signes
    1.70
    Activations Density 2.275%

    No Known Activations