© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250981
    Prev
    Next
    INDEX
    Explanations

    1

    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_56_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
    "],"
    0.37
     بداية
    0.37
    ],"
    0.36
    "];
    0.35
    ப்பின
    0.35
    erequisites
    0.35
    喫
    0.35
    чику
    0.34
    ',"
    0.33
    🏻
    0.33
    POSITIVE LOGITS
    ston
    0.45
     Oo
    0.40
    禕
    0.39
    stv
    0.39
     ranks
    0.37
     što
    0.37
     archbishop
    0.37
    ○○
    0.37
     ants
    0.36
     vivre
    0.36
    Activations Density 0.002%

    No Known Activations