© 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. 164633
    Prev
    Next
    INDEX
    Explanations

    quickly followed by an action

    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
    ৪
    0.29
    ৩
    0.29
    PlainText
    0.26
    pInBuffer
    0.26
    à
    0.26
    Undo
    0.25
    z
    0.25
    x
    0.25
    セプト
    0.25
    etchup
    0.24
    POSITIVE LOGITS
     those
    0.26
     Gao
    0.26
     Cao
    0.26
     being
    0.26
     Auger
    0.26
     их
    0.25
     adulter
    0.25
    ."]
    0.25
     UCLA
    0.25
     these
    0.25
    Activations Density 0.005%

    No Known Activations