© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62798
    Prev
    Next
    INDEX
    Explanations

    koji

    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
    Negative Logits
    0
    1.59
    eg
    1.36
    ，
    1.33
    P
    1.32
    f
    1.31
    ai
    1.30
    R
    1.28
    j
    1.27
    in
    1.25
    for
    1.25
    POSITIVE LOGITS
    য়া
    1.41
    ের
    1.27
    ים
    1.24
     on
    1.21
    ので
    1.08
    یتی
    1.06
    ча
    1.02
    lanır
    1.02
    אן
    0.98
    א
    0.96
    Activations Density 0.000%

    No Known Activations