© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132882
    Prev
    Next
    INDEX
    Explanations

    butterfree, wilder, pidgey, rattata

    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
    us
    1.29
    <0x80>
    1.16
    :
    0.99
    ac
    0.91
    ;
    0.90
    ung
    0.88
    (
    0.88
    ach
    0.87
    {
    0.85
    л
    0.84
    POSITIVE LOGITS
    يل
    1.05
     been
    0.84
    い
    0.76
     网络
    0.73
    </h1>
    0.72
     promote
    0.70
    امة
    0.69
    采
    0.69
    SnackBar
    0.68
    స
    0.68
    Activations Density 0.000%

    No Known Activations