© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202541
    Prev
    Next
    INDEX
    Explanations

    JDBC connection parameters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.56
    க்கொ
    0.55
    过
    0.54
     cuándo
    0.51
    Marcel
    0.50
     Hoping
    0.50
     CheckException
    0.49
     उसने
    0.49
     thawing
    0.49
    他
    0.49
    POSITIVE LOGITS
    ٨
    0.48
    itz
    0.47
    ()"
    0.46
    oad
    0.45
     involvement
    0.45
    ナ
    0.45
    inoa
    0.44
    িয়াল
    0.44
    iy
    0.44
    ного
    0.44
    Activations Density 0.000%

    No Known Activations