© 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. 112456
    Prev
    Next
    INDEX
    Explanations

    thrumming

    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
    م
    1.54
    is
    1.52
    an
    1.49
    on
    1.34
    на
    1.30
    ো
    1.22
    ad
    1.21
    has
    1.16
    the
    1.15
    ம்
    1.13
    POSITIVE LOGITS
    ;
    1.22
     in
    1.18
    8
    0.98
    s
    0.97
     oint
    0.91
    lake
    0.88
    e
    0.87
    rim
    0.86
    lng
    0.86
     πάντα
    0.86
    Activations Density 0.000%

    No Known Activations