© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232730
    Prev
    Next
    INDEX
    Explanations

    growing up with

    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_6_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
    s
    1.38
    a
    1.15
     are
    1.03
    ی
    0.98
    ari
    0.93
    f
    0.91
    é
    0.89
    IN
    0.89
    ivis
    0.88
    ați
    0.86
    POSITIVE LOGITS
     (
    0.91
    ل
    0.85
    ను
    0.83
    ك
    0.81
    应用
    0.79
    會
    0.79
    ب
    0.78
    த்தில்
    0.76
    （
    0.75
    తో
    0.75
    Activations Density 0.000%

    No Known Activations