© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215930
    Prev
    Next
    INDEX
    Explanations

    HERC, HMI, HLS, H(s)

    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
    Negative Logits
    ן
    1.16
    л
    1.05
    inį
    1.02
    inę
    0.99
    escence
    0.95
    rell
    0.93
     be
    0.92
    ctions
    0.92
    se
    0.89
    ası
    0.88
    POSITIVE LOGITS
    其他
    1.32
    ला
    1.24
    ת
    1.23
    ка
    1.21
    ী
    1.16
    де
    1.13
    O
    1.13
    ма
    1.12
    ки
    1.10
    ре
    1.08
    Activations Density 0.012%

    No Known Activations