© 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. 104531
    Prev
    Next
    INDEX
    Explanations

    stability

    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
     άλλ
    1.11
    2
    1.07
    {
    1.07
     öner
    0.98
    ется
    0.94
    <
    0.91
    üd
    0.91
     gerçekleş
    0.91
    𝗱
    0.91
    =
    0.90
    POSITIVE LOGITS
    at
    1.52
    x
    1.23
    is
    1.16
     (
    1.12
     A
    1.09
     F
    1.08
     E
    1.08
     Instrument
    1.07
    त
    1.04
     Auto
    1.02
    Activations Density 0.002%

    No Known Activations