© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25047
    Prev
    Next
    INDEX
    Explanations

    STP and torus

    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_10_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
    ný
    0.63
     květ
    0.60
     přes
    0.51
     pří
    0.51
    řej
    0.50
     Álvarez
    0.50
    </tfoot>
    0.48
     Roberts
    0.48
     Reese
    0.48
    illy
    0.48
    POSITIVE LOGITS
    H
    0.66
    ों
    0.60
     Technol
    0.58
    Can
    0.57
     ENGINEERS
    0.56
     RCMP
    0.55
    initi
    0.55
    Decre
    0.54
    وں
    0.53
    שהו
    0.53
    Activations Density 0.000%

    No Known Activations