© 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. 215415
    Prev
    Next
    INDEX
    Explanations

    variable names x, y, out

    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
     फट
    0.31
     tainted
    0.26
     তাহাকে
    0.26
    Association
    0.25
    భ
    0.25
     associação
    0.25
    Terror
    0.25
    亵
    0.25
     돌
    0.25
    riffe
    0.25
    POSITIVE LOGITS
     digitization
    0.30
    }])
    0.29
    خب
    0.27
    tfine
    0.27
    খো
    0.26
    וי
    0.26
     Incidentally
    0.26
     investments
    0.25
     excavations
    0.25
    izon
    0.25
    Activations Density 0.000%

    No Known Activations