© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112269
    Prev
    Next
    INDEX
    Explanations

    enc, ent, inter, auto

    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_2_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
     to
    1.55
    nt
    1.43
    sh
    1.41
    p
    1.40
    lar
    1.25
     of
    1.23
    ns
    1.21
    su
    1.20
    ls
    1.20
     in
    1.19
    POSITIVE LOGITS
    కు
    1.20
    া
    1.14
    きた
    1.08
    '
    1.01
    ა
    0.98
    お手
    0.96
    aš
    0.95
    a
    0.95
    お知らせ
    0.95
     libera
    0.93
    Activations Density 0.000%

    No Known Activations