© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216688
    Prev
    Next
    INDEX
    Explanations

    have to do

    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_31_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
     embry
    0.37
     appass
    0.37
     하다
    0.37
    槐
    0.37
    王者
    0.36
     облада
    0.36
    inii
    0.36
     Wadd
    0.36
    旳
    0.35
    瞪
    0.35
    POSITIVE LOGITS
     compulsory
    0.39
     obligatoire
    0.39
     impractical
    0.38
    mandatory
    0.38
    clearInterval
    0.37
    ants
    0.37
     obligated
    0.36
    FileChooser
    0.36
     Pflicht
    0.36
     निवड
    0.36
    Activations Density 0.003%

    No Known Activations