© 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. 205966
    Prev
    Next
    INDEX
    Explanations

    r followed by 1 or 0

    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
     to
    1.21
    :
    1.02
     of
    0.99
    ED
    0.98
    ER
    0.89
     la
    0.88
     d
    0.84
     le
    0.84
    ן
    0.81
    ES
    0.80
    POSITIVE LOGITS
    f
    0.87
    家
    0.84
    atthakath
    0.80
    az
    0.78
    ek
    0.76
    ћин
    0.74
     деревя
    0.73
    á
    0.71
    atom
    0.71
     показыва
    0.71
    Activations Density 0.012%

    No Known Activations