© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57441
    Prev
    Next
    INDEX
    Explanations

    uniform, regular, balance

    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_11_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
    ру
    0.65
    ပါ
    0.61
    ем
    0.56
    яз
    0.56
    маты
    0.55
    П
    0.55
     плохо
    0.54
    йн
    0.54
    Collin
    0.53
    פה
    0.53
    POSITIVE LOGITS
    R
    0.70
     R
    0.63
    s
    0.61
     acquittal
    0.59
    ล
    0.59
    atoes
    0.58
    ल
    0.57
     Providers
    0.55
     E
    0.54
    }`,
    0.54
    Activations Density 0.001%

    No Known Activations