© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104081
    Prev
    Next
    INDEX
    Explanations

    sunlight streams through

    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_1_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
    b
    1.45
    c
    1.30
    s
    1.25
    n
    1.24
    g
    1.23
    k
    1.23
    z
    1.23
    ก
    1.16
    d
    1.06
     and
    1.01
    POSITIVE LOGITS
    I
    1.02
    ICK
    0.92
    ंना
    0.91
    .。
    0.89
    \%,
    0.85
    س
    0.84
    വരെ
    0.81
     utilize
    0.80
    ,\\
    0.80
    。<
    0.79
    Activations Density 0.002%

    No Known Activations