© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13682
    Prev
    Next
    INDEX
    Explanations

    words related to formal processes involving documents and communication

    oai_token-act-pair · gemini-2.0-flash

    words related to sharing or providing information

    np_token-act-pair-logits · gpt-4o-mini

    sharing information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    enumi
    -0.59
    ographed
    -0.52
    enumii
    -0.50
     deleteById
    -0.44
     sơ
    -0.43
    奏
    -0.43
     wy
    -0.43
    Espèce
    -0.42
    dymo
    -0.41
    })).
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.73
    ThroughAttribute
    0.63
     provided
    0.61
    曖昧さ回避
    0.60
    provided
    0.60
     shared
    0.60
     humain
    0.59
    supplied
    0.59
    shared
    0.59
     sharing
    0.59
    Activations Density 6.407%

    No Known Activations