© 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. 200336
    Prev
    Next
    INDEX
    Explanations

    computer commands

    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
     MERCHANTABILITY
    0.44
     mutual
    0.40
     Mutual
    0.39
     Kr
    0.38
    ಿನಲ್ಲಿ
    0.38
     Eden
    0.36
    各有
    0.36
    譲
    0.36
    ikel
    0.35
    ਏ
    0.35
    POSITIVE LOGITS
    StringType
    0.40
     Srb
    0.39
    ыз
    0.39
     inp
    0.38
    wrist
    0.38
    ussia
    0.38
    aje
    0.37
    urno
    0.37
    व्र
    0.37
    ímp
    0.37
    Activations Density 0.001%

    No Known Activations