© 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. 49401
    Prev
    Next
    INDEX
    Explanations

    function prototypes

    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
    MT
    0.37
     തുറ
    0.36
    HA
    0.36
     याचा
    0.35
    Polish
    0.34
    Mé
    0.34
    Ž
    0.34
     HA
    0.33
    延長
    0.33
    antwort
    0.33
    POSITIVE LOGITS
    ClInclude
    0.40
     görül
    0.39
    roft
    0.38
     dav
    0.37
     messes
    0.36
     rarement
    0.36
    injlim
    0.36
    fillStyle
    0.35
    𝒉
    0.35
    olin
    0.35
    Activations Density 0.000%

    No Known Activations