© 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. 31510
    Prev
    Next
    INDEX
    Explanations

    M

    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
    ক্সি
    0.42
    屿
    0.42
     Ko
    0.40
     ko
    0.40
    夎
    0.38
     isotropic
    0.38
    nicu
    0.38
     ellips
    0.37
    罩
    0.37
     मृत्यु
    0.37
    POSITIVE LOGITS
    GV
    0.51
    NB
    0.45
    gb
    0.45
    fare
    0.44
    аз
    0.40
     fare
    0.39
    GB
    0.39
    gs
    0.39
     कोर्ट
    0.39
     fits
    0.38
    Activations Density 0.006%

    No Known Activations