© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254244
    Prev
    Next
    INDEX
    Explanations

    word starts with H

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    hô
    0.41
    hanna
    0.40
    hay
    0.39
    hé
    0.38
    郘
    0.38
    hon
    0.38
    hive
    0.36
    hak
    0.35
    hik
    0.34
    hled
    0.34
    POSITIVE LOGITS
     Holders
    0.45
     الح
    0.44
     Hundreds
    0.43
     Holder
    0.41
     Http
    0.41
     Hoping
    0.40
     Handle
    0.39
     Heads
    0.39
    ൈ
    0.38
     Hours
    0.38
    Activations Density 0.012%

    No Known Activations