© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213976
    Prev
    Next
    INDEX
    Explanations

    bruschetta, parrots, Elbrus

    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_5_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
     вас
    0.98
    8
    0.96
    맟
    0.90
    6
    0.89
    <unused2164>
    0.88
    F
    0.87
     രൂപ
    0.85
     разрабо
    0.84
     као
    0.84
     پسر
    0.84
    POSITIVE LOGITS
    at
    1.42
    in
    1.36
    il
    1.32
    u
    1.32
    r
    1.21
    c
    1.16
    z
    1.15
    t
    1.12
    a
    1.09
    w
    1.09
    Activations Density 0.000%

    No Known Activations