© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42669
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_22_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
     six
    0.29
    six
    0.27
     nine
    0.27
     V
    0.26
     Savannah
    0.26
     ছয়
    0.26
     മാര്‍
    0.25
    mal
    0.24
    0.24
     eight
    0.24
    POSITIVE LOGITS
    Также
    0.27
     théorème
    0.26
    icherweise
    0.26
    ChessBot
    0.26
    寘
    0.26
     corretamente
    0.25
    Кроме
    0.25
     Bühne
    0.25
    طاء
    0.25
    Missense
    0.25
    Activations Density 0.004%

    No Known Activations