© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36299
    Prev
    Next
    INDEX
    Explanations

    In prefixes

    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_50_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
    izowane
    0.42
    headless
    0.41
    Consec
    0.41
    Loire
    0.40
    換え
    0.39
    弩
    0.38
     আন্দ
    0.38
    Heinrich
    0.38
     সফরে
    0.36
     Nuk
    0.36
    POSITIVE LOGITS
    커
    0.44
     పె
    0.37
     سين
    0.35
     পা
    0.34
     hamstring
    0.34
     Revenues
    0.34
    耆
    0.34
     Sinai
    0.34
     rung
    0.34
    SIN
    0.33
    Activations Density 0.000%

    No Known Activations