© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228482
    Prev
    Next
    INDEX
    Explanations

    citation numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    -/
    0.40
    guards
    0.39
    ੪
    0.39
    submissions
    0.39
     Ij
    0.39
    -]
    0.38
    bond
    0.38
    얽
    0.38
    -)
    0.38
    gk
    0.37
    POSITIVE LOGITS
    igenza
    0.43
     ounce
    0.38
     ounces
    0.37
    '
    0.37
     likes
    0.37
    бл
    0.34
    ნ
    0.34
     pag
    0.34
     fin
    0.33
    agens
    0.33
    Activations Density 0.000%

    No Known Activations