© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210387
    Prev
    Next
    INDEX
    Explanations

    help me / on the edge

    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_5_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
    at
    2.59
    ي
    2.08
    as
    1.81
    i
    1.74
    are
    1.49
    on
    1.47
    it
    1.43
    am
    1.43
    is
    1.42
    al
    1.40
    POSITIVE LOGITS
    𝐞
    0.83
     मीणा
    0.81
    ιών
    0.81
    می
    0.80
    서는
    0.80
    縈
    0.80
    ί
    0.79
    龴
    0.78
    주고
    0.77
    ूप
    0.77
    Activations Density 0.009%

    No Known Activations