© 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. 161597
    Prev
    Next
    INDEX
    Explanations

    Indian states or territories

    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
    '
    1.81
    o
    1.16
    ’
    1.11
    .
    1.08
    al
    1.06
     in
    1.04
    이었다
    1.01
    ANIM
    0.98
    在
    0.96
    e
    0.95
    POSITIVE LOGITS
    ä
    1.16
    ک
    1.10
     powied
    1.08
    א
    0.95
     überzeugt
    0.94
    á
    0.93
     söyled
    0.89
    습니다
    0.89
     отмети
    0.88
    č
    0.87
    Activations Density 0.001%

    No Known Activations