© 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. 58434
    Prev
    Next
    INDEX
    Explanations

    Paramahansa Yogananda

    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
    ру
    1.29
    ка
    1.25
    ו
    1.25
    و
    1.09
    2
    1.08
    ня
    1.07
    nél
    1.06
    ми
    1.05
    -
    1.04
    м
    0.99
    POSITIVE LOGITS
     in
    1.13
     در
    1.05
     to
    1.03
    یک
    0.94
    ot
    0.93
     a
    0.91
    od
    0.87
    かかる
    0.87
    and
    0.86
    cd
    0.86
    Activations Density 0.000%

    No Known Activations