© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33260
    Prev
    Next
    INDEX
    Explanations

    website links .article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    瀛
    0.37
    डोर
    0.36
    istasis
    0.36
    ستہ
    0.36
    ことがある
    0.36
     autof
    0.35
     Woodstock
    0.35
     autoWatch
    0.35
     சிகிச்ச
    0.35
     لذا
    0.34
    POSITIVE LOGITS
    価
    0.42
     cổng
    0.41
     kern
    0.40
     iam
    0.39
    FLP
    0.39
     ReturnVal
    0.38
     UML
    0.38
     curvature
    0.37
     rams
    0.37
    CIAL
    0.37
    Activations Density 0.000%

    No Known Activations