© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122041
    Prev
    Next
    INDEX
    Explanations

    minutes

    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_38_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
     metres
    0.39
     halved
    0.39
    ર્ક
    0.38
     centimeters
    0.37
     tilted
    0.37
     %).
    0.37
    atius
    0.37
    Lk
    0.36
     monotonic
    0.35
     extent
    0.35
    POSITIVE LOGITS
    subscriptions
    0.40
     pch
    0.39
    ಚ್ಚ
    0.39
    ácil
    0.38
    징
    0.38
    Getenv
    0.38
     MX
    0.37
     solaire
    0.37
     scegli
    0.37
    reader
    0.37
    Activations Density 0.002%

    No Known Activations