© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231618
    Prev
    Next
    INDEX
    Explanations

    muting others

    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_6_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
     to
    1.63
    to
    1.33
    z
    1.16
    b
    1.09
     has
    1.09
    <0x0D>
    1.06
    and
    1.06
    c
    1.05
     a
    1.05
    x
    1.03
    POSITIVE LOGITS
    .
    1.02
    ระหว่าง
    0.89
     जिसके
    0.84
     caregiver
    0.83
    reatment
    0.82
     precursor
    0.82
    áról
    0.80
     hvilket
    0.80
     نمی‌
    0.79
    ΡΙ
    0.77
    Activations Density 0.000%

    No Known Activations