© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26215
    Prev
    Next
    INDEX
    Explanations

    graduation

    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
    م
    0.76
    Man
    0.74
    Re
    0.71
    ’
    0.71
    N
    0.68
    מ
    0.68
     i
    0.66
    M
    0.66
    add
    0.66
    India
    0.66
    POSITIVE LOGITS
     vattati
    0.62
    ıyla
    0.60
     adhipp
    0.59
     generación
    0.56
    ués
    0.56
     patitth
    0.55
     pavatt
    0.55
     crucified
    0.54
     yattha
    0.54
    ющему
    0.54
    Activations Density 0.008%

    No Known Activations