© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35817
    Prev
    Next
    INDEX
    Explanations

    faith in

    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_11_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
     ordine
    0.58
    ็ม
    0.55
     будут
    0.54
    ش
    0.53
     distribuzione
    0.52
    на
    0.51
    ма
    0.51
    нима
    0.51
    ْد
    0.51
    年月日
    0.51
    POSITIVE LOGITS
     s
    0.68
     Becker
    0.56
     r
    0.55
    ->
    0.55
     i
    0.54
     프리
    0.54
     Vance
    0.54
     Boynton
    0.53
    vann
    0.53
     Contreras
    0.53
    Activations Density 0.001%

    No Known Activations