© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136209
    Prev
    Next
    INDEX
    Explanations

    1 followed by BC, engine, or numbers

    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_12_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
    δος
    0.18
    ressione
    0.18
    λη
    0.17
    اشة
    0.17
    ências
    0.17
    aszt
    0.17
    plc
    0.17
    ukset
    0.17
    h
    0.16
    𓂀
    0.16
    POSITIVE LOGITS
     thanking
    0.19
     answers
    0.17
     beantwort
    0.17
    團隊
    0.16
     keber
    0.16
     человек
    0.15
     imponer
    0.15
     memenuhi
    0.15
     motivos
    0.15
     meaningfully
    0.15
    Activations Density 0.000%

    No Known Activations