© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169934
    Prev
    Next
    INDEX
    Explanations

    formatting and code

    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_56_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
     D
    2.22
     الد
    1.77
     Д
    1.75
    D
    1.41
     הד
    1.35
     ด
    1.23
     ড
    1.22
     dé
    1.20
     ड
    1.18
     د
    1.17
    POSITIVE LOGITS
     Popular
    0.40
    Popular
    0.40
     जन
    0.40
    ちな
    0.35
    displayName
    0.35
    人気の
    0.35
    ളി
    0.33
     displayName
    0.33
    DIG
    0.33
     doGet
    0.33
    Activations Density 0.005%

    No Known Activations