© 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. 54053
    Prev
    Next
    INDEX
    Explanations

    percentage change percentage difference

    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
    غراف
    0.41
     absol
    0.38
     programmi
    0.37
    కొని
    0.35
     isolated
    0.35
    炒
    0.35
    current
    0.35
    unteers
    0.35
    ジナル
    0.34
    కుని
    0.34
    POSITIVE LOGITS
    霈
    0.38
     {%
    0.36
    Diane
    0.34
    LISTEN
    0.34
    FIG
    0.34
    Liter
    0.34
     कलम
    0.33
    {%
    0.33
    奄
    0.33
    Sentence
    0.33
    Activations Density 0.000%

    No Known Activations