© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197664
    Prev
    Next
    INDEX
    Explanations

    blip or bluetooth

    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_4_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
    r
    1.03
    ilah
    0.91
    C
    0.90
    I
    0.89
    il
    0.88
    Group
    0.87
    ts
    0.83
    <
    0.83
    K
    0.83
    (
    0.82
    POSITIVE LOGITS
    ために
    1.14
    ى
    0.97
    ation
    0.93
     człowie
    0.89
    ם
    0.89
     manera
    0.85
     taki
    0.84
     диа
    0.84
     který
    0.84
     múltipl
    0.84
    Activations Density 0.000%

    No Known Activations