© 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. 23758
    Prev
    Next
    INDEX
    Explanations

    disc/disk/dish

    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
     সন্ন
    0.37
    ਐ
    0.37
    ocortic
    0.35
    协调
    0.34
     कॉनकॉर्ड
    0.34
    accordo
    0.34
    Է
    0.34
    કો
    0.33
     harmony
    0.32
     harb
    0.32
    POSITIVE LOGITS
     disc
    2.42
     Disc
    1.98
     dish
    1.96
    disc
    1.84
    Disc
    1.84
     диск
    1.64
     Dish
    1.63
     disk
    1.61
    Dish
    1.55
     discs
    1.52
    Activations Density 0.045%

    No Known Activations