© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48550
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

    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_31_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
    ifle
    0.42
    ifical
    0.42
    issan
    0.41
    \}
    0.39
    基地
    0.38
    ifiziert
    0.36
     frictionless
    0.36
    假期
    0.36
    埤
    0.36
    underset
    0.36
    POSITIVE LOGITS
     uppercase
    0.44
    uppercase
    0.43
     doubling
    0.41
     تربيع
    0.41
     পাল্টা
    0.40
    Odd
    0.39
     doubled
    0.38
    ดาว
    0.38
     countdown
    0.38
    訛
    0.37
    Activations Density 0.172%

    No Known Activations