© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60206
    Prev
    Next
    INDEX
    Explanations

    higher is better

    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
    는
    1.20
    is
    1.09
    ت
    1.05
     are
    1.03
    は
    0.98
    {
    0.90
    是
    0.86
    os
    0.81
    are
    0.78
    an
    0.74
    POSITIVE LOGITS
    ’
    0.91
     I
    0.80
    IS
    0.79
    CH
    0.77
    ر
    0.74
    ER
    0.73
    LE
    0.69
    ો
    0.69
     essendo
    0.68
    ﻟ
    0.68
    Activations Density 0.007%

    No Known Activations