© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248709
    Prev
    Next
    INDEX
    Explanations

    new

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ly
    0.40
    または
    0.36
    лиз
    0.35
     তাও
    0.34
    里
    0.34
    емость
    0.34
    лесо
    0.34
    ﺯ
    0.33
     favoured
    0.33
    重要な
    0.33
    POSITIVE LOGITS
     लर्निंग
    0.39
     jumper
    0.37
     learning
    0.36
     cerdo
    0.36
    ᴴ
    0.36
    Com
    0.36
     Blumen
    0.36
     help
    0.36
     Multiplayer
    0.35
     credit
    0.35
    Activations Density 0.001%

    No Known Activations