© 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. 12816
    Prev
    Next
    INDEX
    Explanations

    questions followed by context

    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
    ูก
    0.52
    м
    0.52
    ύ
    0.51
    в
    0.51
    ม
    0.51
    It
    0.50
    gnię
    0.50
    ə
    0.50
    ี่
    0.50
    о
    0.49
    POSITIVE LOGITS
     Exodus
    0.50
    FAKE
    0.47
     LI
    0.47
    ARDS
    0.46
    CBC
    0.46
     Wordsworth
    0.44
     LaF
    0.44
    EXIT
    0.44
     Arithmetic
    0.43
     Archipelago
    0.42
    Activations Density 0.001%

    No Known Activations