© 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. 130060
    Prev
    Next
    INDEX
    Explanations

    names

    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
    LAMP
    0.41
    ListNode
    0.40
    㖷
    0.39
    FloatTensor
    0.36
    يله
    0.36
     способности
    0.36
     опор
    0.36
    㗊
    0.36
    longrightarrow
    0.35
     ஆன்
    0.35
    POSITIVE LOGITS
     ADA
    0.47
     Gow
    0.46
     Sch
    0.44
     GSH
    0.44
     Sheridan
    0.44
     Ass
    0.43
     Robert
    0.42
     Ull
    0.42
     Ades
    0.41
     Heid
    0.41
    Activations Density 0.000%

    No Known Activations