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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4820
    Prev
    Next
    INDEX
    Explanations

    mentions of time points in complex scientific experiments

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'sub' or numerical values

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

    numbers in calculations

    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
    ]--;
    -0.77
    XmlAccessType
    -0.75
     समीक्षाओं
    -0.74
     متعلقه
    -0.74
    ⋙
    -0.70
     JpaRepository
    -0.69
     Jefus
    -0.69
    InjectAttribute
    -0.68
    ngrx
    -0.67
     Référence
    -0.66
    POSITIVE LOGITS
     sub
    0.51
     fourteen
    0.49
    ̍t
    0.47
     Fourteen
    0.44
    geführt
    0.43
     must
    0.43
    FieldBuilder
    0.43
    7
    0.42
    wo
    0.40
    sub
    0.40
    Activations Density 4.686%

    No Known Activations