© 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. 162312
    Prev
    Next
    INDEX
    Explanations

    8 followed by ">"

    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
    調整
    0.40
    ƒ
    0.40
    门口
    0.38
     cvec
    0.37
     surnames
    0.36
     sod
    0.36
     شر
    0.36
    segment
    0.36
     リビング
    0.35
     افتتاح
    0.35
    POSITIVE LOGITS
    ตา
    0.42
     Enter
    0.40
    Strength
    0.39
     Ψ
    0.39
    λλη
    0.38
     delegation
    0.37
     Delegation
    0.37
     Cl
    0.37
     λ
    0.37
     Charg
    0.36
    Activations Density 0.000%

    No Known Activations