© 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. 59077
    Prev
    Next
    INDEX
    Explanations

    has/hacer

    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
    ле
    1.45
    σης
    1.07
    ಾ
    1.04
    ur
    1.03
    ча
    0.98
    यों
    0.97
    ას
    0.95
     Hrvatske
    0.95
     Hrvatskoj
    0.95
    kana
    0.94
    POSITIVE LOGITS
     in
    1.24
    ING
    0.94
    在
    0.94
    ă
    0.91
    한
    0.89
    是
    0.88
    с
    0.84
    0
    0.84
    nd
    0.83
     is
    0.83
    Activations Density 0.007%

    No Known Activations