© 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. 104350
    Prev
    Next
    INDEX
    Explanations

    pests

    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
    {
    1.30
    。
    1.13
    ।
    1.06
    ។
    1.02
    (
    0.97
     (
    0.96
    H
    0.94
     يا
    0.93
    Yea
    0.93
     ايجاد
    0.92
    POSITIVE LOGITS
    ra
    1.18
    ل
    1.09
    z
    1.00
    них
    0.96
    ре
    0.93
    w
    0.93
     and
    0.92
    ri
    0.91
    vian
    0.89
    v
    0.89
    Activations Density 0.000%

    No Known Activations