© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121455
    Prev
    Next
    INDEX
    Explanations

    Musk

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    '
    0.89
    (
    0.77
    )
    0.71
    <0x80>
    0.68
    :
    0.65
    ;
    0.63
    AR
    0.60
    ஸ்
    0.59
    UL
    0.59
    ),
    0.58
    POSITIVE LOGITS
    ма
    1.02
    ৮
    0.82
    ף
    0.82
    to
    0.81
    на
    0.75
    മ
    0.73
    مت
    0.71
    ८
    0.70
    느
    0.68
    대
    0.67
    Activations Density 0.000%

    No Known Activations