© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44615
    Prev
    Next
    INDEX
    Explanations

    tokens delims

    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_13_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
    。"
    0.66
    "
    0.60
    ."
    0.53
     flusso
    0.53
    …"
    0.49
    ."[
    0.48
     dicho
    0.48
    uvre
    0.48
     ,"
    0.47
     chirp
    0.47
    POSITIVE LOGITS
     anderes
    0.66
    ڡ
    0.64
    others
    0.62
    سه
    0.62
     other
    0.61
     अन्य
    0.58
     hrs
    0.58
    다른
    0.58
     otras
    0.57
     άλλα
    0.57
    Activations Density 0.002%

    No Known Activations