© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171585
    Prev
    Next
    INDEX
    Explanations

    zipper closure

    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_20_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
    蛄
    0.45
    ospheric
    0.43
    炁
    0.42
     뭘
    0.41
    Disable
    0.41
    缓慢
    0.39
     Suppression
    0.39
    📩
    0.39
    但不
    0.39
    ēi
    0.39
    POSITIVE LOGITS
     pribadi
    0.46
     völlig
    0.44
     ständig
    0.44
     was
    0.42
     bakteri
    0.42
     bev
    0.41
     hosszú
    0.41
     sparen
    0.41
     indes
    0.41
     bef
    0.40
    Activations Density 0.000%

    No Known Activations