© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179658
    Prev
    Next
    INDEX
    Explanations

    finding indices of max/min/sorted

    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_24_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
    Against
    0.48
    against
    0.43
    EnableCOMDAT
    0.41
    February
    0.39
    Hy
    0.39
    ɧ
    0.39
    ıları
    0.39
    Hat
    0.38
    AntiForgery
    0.38
     Against
    0.38
    POSITIVE LOGITS
    쁨
    0.41
     king
    0.41
     받을
    0.40
     connexion
    0.38
     причем
    0.38
     infarction
    0.37
     പ്രവര്‍
    0.37
     thé
    0.37
     hottest
    0.36
     npm
    0.36
    Activations Density 0.001%

    No Known Activations