© 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. 62924
    Prev
    Next
    INDEX
    Explanations

    revolve around

    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
    し
    2.09
    ৫
    1.45
    中
    1.38
    ب
    1.38
    ني
    1.36
    值
    1.35
     is
    1.31
    使用
    1.30
    ので
    1.30
    ని
    1.29
    POSITIVE LOGITS
    he
    1.49
    al
    1.42
    all
    1.40
    are
    1.40
    od
    1.38
    et
    1.34
    ent
    1.33
    or
    1.31
    ic
    1.31
    p
    1.28
    Activations Density 0.001%

    No Known Activations