© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130063
    Prev
    Next
    INDEX
    Explanations

    ny

    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
    ه
    1.23
    a
    1.08
    .
    1.05
     in
    1.02
    0
    0.86
    elling
    0.86
    া
    0.84
    们
    0.84
    ining
    0.82
    ridges
    0.81
    POSITIVE LOGITS
    л
    1.34
    ו
    0.99
     уви
    0.91
    はじ
    0.87
    する
    0.87
    お願い
    0.85
     éventuellement
    0.84
     powied
    0.83
    δό
    0.83
     слегка
    0.83
    Activations Density 0.000%

    No Known Activations