© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44047
    Prev
    Next
    INDEX
    Explanations

    signing policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     régulière
    0.55
     \&
    0.49
     \%$
    0.47
     Keyes
    0.47
     गेम्स
    0.46
    ’?
    0.46
     NOV
    0.46
    .•
    0.45
    Disclosure
    0.45
     tỏa
    0.45
    POSITIVE LOGITS
    I
    0.44
    ungal
    0.44
    ylated
    0.43
    esch
    0.43
    テ
    0.42
     habitat
    0.42
    unan
    0.42
     comprimento
    0.42
    ic
    0.41
    ids
    0.41
    Activations Density 0.002%

    No Known Activations