© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206505
    Prev
    Next
    INDEX
    Explanations

    preced ate

    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_10_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
    datos
    0.79
    С
    0.75
    އ
    0.72
     heirs
    0.72
    N
    0.71
     their
    0.70
    ಬ
    0.69
    Egypt
    0.68
    Came
    0.68
    estrut
    0.67
    POSITIVE LOGITS
    ien
    0.89
    ada
    0.75
    ina
    0.73
    UL
    0.73
    או
    0.72
    า
    0.71
    на
    0.70
    UD
    0.70
     осуществ
    0.70
    ULL
    0.69
    Activations Density 0.000%

    No Known Activations