© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175252
    Prev
    Next
    INDEX
    Explanations

    curiosity and asking questions

    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_24_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
    畋
    0.35
    League
    0.35
    开关
    0.35
     fn
    0.34
     League
    0.34
     Default
    0.34
     recapt
    0.34
    طع
    0.34
     Figaro
    0.33
     غ
    0.33
    POSITIVE LOGITS
     ngunit
    0.43
    стане
    0.42
     rév
    0.42
     Hanson
    0.42
     pinning
    0.41
    Fot
    0.41
    ங்களையும்
    0.41
    icule
    0.40
    but
    0.39
    મી
    0.39
    Activations Density 0.003%

    No Known Activations