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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 34157
    Prev
    Next
    INDEX
    Explanations

    confidential services

    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
    ்து
    0.42
    待ち
    0.41
    llam
    0.38
     कामया
    0.37
     baja
    0.37
    YNAM
    0.37
     ज्व
    0.36
    晴
    0.36
    Specificity
    0.36
    puls
    0.36
    POSITIVE LOGITS
     Chico
    0.43
     chlor
    0.41
     Solicitor
    0.39
    osito
    0.39
     unfair
    0.38
     Abo
    0.37
     Bertrand
    0.37
     Men
    0.37
     végét
    0.36
     Anfield
    0.36
    Activations Density 0.006%

    No Known Activations