© 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. 41833
    Prev
    Next
    INDEX
    Explanations

    at an

    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
    il
    0.80
    ى
    0.79
    يل
    0.73
     usuario
    0.71
    پيديا
    0.67
    ции
    0.65
     cotidiana
    0.60
     nœ
    0.60
    ía
    0.59
    يد
    0.59
    POSITIVE LOGITS
    S
    0.73
    N
    0.73
    K
    0.73
    M
    0.70
     和
    0.69
    Color
    0.68
    have
    0.67
    Set
    0.64
    F
    0.64
    Top
    0.64
    Activations Density 0.011%

    No Known Activations