© 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. 157557
    Prev
    Next
    INDEX
    Explanations

    all is safe

    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
    t
    1.51
    in
    1.36
     in
    1.26
    d
    1.22
    ances
    1.21
    т
    1.19
     on
    1.18
    är
    1.09
    ira
    1.07
    н
    1.07
    POSITIVE LOGITS
    1
    1.17
     katva
    1.08
    ம்
    1.03
    ată
    0.98
     seab
    0.97
    م
    0.94
     sesu
    0.92
    はい
    0.91
    았
    0.91
    ει
    0.90
    Activations Density 0.000%

    No Known Activations