© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126947
    Prev
    Next
    INDEX
    Explanations

    Swiss Mountain Dog

    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
    는
    0.70
    し
    0.69
    ने
    0.68
    л
    0.67
    ل
    0.67
    nesday
    0.65
    δί
    0.62
    ла
    0.61
    typed
    0.61
    መሳሳይ
    0.60
    POSITIVE LOGITS
     for
    0.71
    ’
    0.67
    5
    0.64
     Normandy
    0.63
     Ecole
    0.59
     École
    0.59
     by
    0.58
     welke
    0.58
     garage
    0.58
    *
    0.58
    Activations Density 0.000%

    No Known Activations