© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    U.S. legal citations

    oai_token-act-pair · gemini-2.0-flash

    say "d"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Roskov
    -0.59
    bitkan
    -0.53
     himo
    -0.52
     resourceCulture
    -0.50
    IntoConstraints
    -0.49
    +#+#
    -0.49
    StoryboardSegue
    -0.47
     TType
    -0.46
    uyên
    -0.44
     unknownFields
    -0.43
    POSITIVE LOGITS
     D
    1.63
    D
    1.56
     De
    1.30
    De
    1.23
    Ｄ
    1.21
    Ds
    1.16
    Dt
    1.14
     Du
    1.14
     Dt
    1.14
     Д
    1.12
    Activations Density 4.686%

    No Known Activations