© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141139
    Prev
    Next
    INDEX
    Explanations

    package installation

    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_12_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
    ?')
    0.39
    椋
    0.33
    ënten
    0.33
     ລັບ
    0.32
     футболдук
    0.31
    вав
    0.30
    ूपी
    0.30
     শুরু
    0.30
    ième
    0.30
    ✴
    0.30
    POSITIVE LOGITS
    u
    0.46
    g
    0.46
    o
    0.45
    v
    0.43
    y
    0.42
     griego
    0.38
    k
    0.38
    ribute
    0.38
    m
    0.37
     Gottes
    0.36
    Activations Density 0.002%

    No Known Activations