© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39810
    Prev
    Next
    INDEX
    Explanations

    one

    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_57_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
     Respondent
    0.40
     Defendant
    0.38
    وبت
    0.37
    염
    0.36
     Claimant
    0.36
     petitioner
    0.36
     claimant
    0.35
     Usuario
    0.35
     जायेगी
    0.35
     কর্মকর্তা
    0.35
    POSITIVE LOGITS
    pages
    0.56
     l
    0.47
    three
    0.42
     liné
    0.42
     pagine
    0.41
    Pages
    0.41
    ременно
    0.40
     pages
    0.40
    centage
    0.40
    seiten
    0.40
    Activations Density 0.005%

    No Known Activations