© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161766
    Prev
    Next
    INDEX
    Explanations

    square root of

    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_31_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
     Sof
    0.38
    .__
    0.38
     ба
    0.35
     Ov
    0.35
     حضور
    0.34
    Res
    0.34
     ningún
    0.34
    yni
    0.34
    Sof
    0.34
    不起
    0.33
    POSITIVE LOGITS
    pples
    0.39
     amus
    0.39
     क्वेश्चंस
    0.39
    pubescens
    0.37
    组合
    0.37
     kombin
    0.37
    ಿಕೊಳ್ಳ
    0.37
     الحر
    0.36
    🥔
    0.36
    atorics
    0.36
    Activations Density 0.000%

    No Known Activations