© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213578
    Prev
    Next
    INDEX
    Explanations

    @

    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_43_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
     flow
    0.39
    ਹੀ
    0.37
    structure
    0.36
     camel
    0.35
     δο
    0.34
     __
    0.33
     ترجم
    0.33
    рованная
    0.33
     ہونے
    0.33
    rupt
    0.32
    POSITIVE LOGITS
     initiates
    0.38
    othek
    0.37
     Algebras
    0.37
    stechnik
    0.37
    谶
    0.37
    荖
    0.37
     inizia
    0.37
    ipsych
    0.36
    .".,
    0.36
     technik
    0.36
    Activations Density 0.001%

    No Known Activations