© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87460
    Prev
    Next
    INDEX
    Explanations

    aex

    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_3_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
    টি
    0.75
     arou
    0.68
     I
    0.67
     costru
    0.67
     impor
    0.64
     notre
    0.63
     esterno
    0.63
     quantos
    0.63
    aund
    0.63
     vernacular
    0.63
    POSITIVE LOGITS
    زى
    0.84
    ار
    0.77
    9
    0.74
    та
    0.70
    на
    0.69
    א
    0.68
    र
    0.68
    你
    0.66
    تى
    0.64
    2
    0.64
    Activations Density 0.003%

    No Known Activations