© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207782
    Prev
    Next
    INDEX
    Explanations

    protected routes

    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_19_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
    рёх
    0.47
     arasında
    0.45
     prij
    0.44
    asında
    0.42
     தரும்
    0.42
     помещения
    0.42
     две
    0.41
     ه
    0.40
     definidas
    0.40
    最早
    0.40
    POSITIVE LOGITS
    OPHY
    0.47
    мы
    0.44
    ELL
    0.43
     वेदा
    0.43
    ifica
    0.42
     پاکستان
    0.42
     পাকিস্তানি
    0.42
     repudi
    0.42
     पाकिस्तानी
    0.42
     Autof
    0.42
    Activations Density 0.000%

    No Known Activations