© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224424
    Prev
    Next
    INDEX
    Explanations

    project and opportunity initiative

    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_10_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
     harmonize
    0.54
     imitate
    0.53
     pdelay
    0.53
    แทน
    0.52
     parametr
    0.52
    സോ
    0.52
    ን
    0.52
     circulate
    0.52
     delect
    0.51
     conecta
    0.51
    POSITIVE LOGITS
    （
    0.41
    <0xE3>
    0.41
    ），
    0.40
    $),
    0.40
     Caps
    0.40
    sin
    0.39
    들이
    0.39
    ributions
    0.39
     Perkin
    0.39
    ك
    0.39
    Activations Density 0.000%

    No Known Activations