© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90194
    Prev
    Next
    INDEX
    Explanations

    warmth, control, specific button

    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_23_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
     topik
    0.41
     vorige
    0.40
     každ
    0.38
     mae
    0.38
     fok
    0.38
     käyttö
    0.36
     صہیونی
    0.36
    渍
    0.36
     neer
    0.36
     könnte
    0.35
    POSITIVE LOGITS
     turb
    0.41
     Permissions
    0.40
    ché
    0.39
    abez
    0.39
    మంది
    0.38
    wherein
    0.38
    adolu
    0.38
     Adem
    0.38
    agawa
    0.37
     Beni
    0.37
    Activations Density 0.000%

    No Known Activations