© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211018
    Prev
    Next
    INDEX
    Explanations

    SA

    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_43_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
    laşt
    0.40
    ımın
    0.39
    佃
    0.37
    ារ
    0.37
    ைக்
    0.37
     SD
    0.36
     revealing
    0.36
     PDP
    0.36
    માન
    0.36
    ୂ
    0.36
    POSITIVE LOGITS
     Co
    0.40
     Cook
    0.39
    scroll
    0.39
     Scroll
    0.39
    ockets
    0.39
     Guard
    0.38
    retch
    0.38
    ματα
    0.38
     yat
    0.37
     Archive
    0.36
    Activations Density 0.001%

    No Known Activations