© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206712
    Prev
    Next
    INDEX
    Explanations

    detail, details, or asking for specifics

    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_37_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
    glas
    0.43
    ность
    0.40
     പുതിയ
    0.40
    getRequest
    0.39
    บริษัท
    0.38
    ımda
    0.37
    )=
    0.36
     可以
    0.36
     bedrijf
    0.35
    กีฬา
    0.35
    POSITIVE LOGITS
     జాగ్ర
    0.40
     اعتبار
    0.39
     detail
    0.39
     details
    0.38
     дета
    0.38
     qualunque
    0.37
     detalle
    0.37
     cualquiera
    0.36
     détail
    0.36
     พิจ
    0.36
    Activations Density 0.005%

    No Known Activations