© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155761
    Prev
    Next
    INDEX
    Explanations

    conversational filler

    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_60_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
     I
    0.93
    I
    0.44
     Now
    0.44
     IUser
    0.40
     Теперь
    0.40
    "
    0.40
    .
    0.39
    𝐼
    0.39
     Ι
    0.38
     Ahora
    0.38
    POSITIVE LOGITS
     ;
    0.70
    .;
    0.63
    ;
    0.59
     ;,
    0.55
     wonderful
    0.54
     will
    0.54
     great
    0.54
    ;</
    0.52
     fantastic
    0.52
    great
    0.52
    Activations Density 0.001%

    No Known Activations