© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57297
    Prev
    Next
    INDEX
    Explanations

    rather followed by descriptive words

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ：
    0.66
    ਪ
    0.66
    kiej
    0.65
    amente
    0.62
     médicas
    0.62
    áo
    0.61
    ル
    0.61
    پ
    0.60
    К
    0.60
     esenciales
    0.59
    POSITIVE LOGITS
     Il
    0.70
     Six
    0.69
     Val
    0.66
     Wild
    0.66
     Rom
    0.62
     Pittsburgh
    0.62
     CPM
    0.62
     Dir
    0.61
     Liverpool
    0.61
     Vel
    0.61
    Activations Density 0.000%

    No Known Activations