© 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. 207200
    Prev
    Next
    INDEX
    Explanations

    primary need

    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
    t
    0.52
     навіть
    0.50
    Professional
    0.46
     technicians
    0.45
     Breast
    0.45
    Breast
    0.45
    As
    0.44
    I
    0.44
    Even
    0.43
     चिकित्सकों
    0.43
    POSITIVE LOGITS
     නිෂ්
    0.54
    𒊬
    0.54
    avacanam
    0.52
     නො
    0.51
    }^{*}(
    0.50
    Соцмережа
    0.50
     warmly
    0.50
     غیر
    0.50
    rarea
    0.50
    --*/
    0.50
    Activations Density 0.000%

    No Known Activations