© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214543
    Prev
    Next
    INDEX
    Explanations

    Brumario / Makemake

    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
    P
    1.53
    X
    1.39
    R
    1.30
    C
    1.27
    B
    1.24
    T
    1.13
    D
    1.13
    G
    1.07
    M
    1.05
    V
    1.01
    POSITIVE LOGITS
    <0x0D>
    1.38
    '
    1.12
    \
    1.06
    ни
    1.02
    <0x80>
    0.94
    يل
    0.87
    ’
    0.86
    н
    0.86
    '=>$
    0.85
     числа
    0.84
    Activations Density 0.000%

    No Known Activations