© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200256
    Prev
    Next
    INDEX
    Explanations

    one-upping

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ASSESSMENT
    0.40
     assessment
    0.40
    राब
    0.39
     вещей
    0.39
     Assessment
    0.38
     things
    0.38
     THINGS
    0.38
    ّد
    0.38
     assessments
    0.36
     stvari
    0.36
    POSITIVE LOGITS
    kan
    0.50
    heben
    0.48
    innan
    0.46
    Kan
    0.43
    KAN
    0.43
    aruhi
    0.42
    Commenting
    0.42
    teren
    0.41
    kmeans
    0.41
    meti
    0.41
    Activations Density 0.000%

    No Known Activations