© 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. 200390
    Prev
    Next
    INDEX
    Explanations

    groups or collections

    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
    楢
    0.38
     disregarding
    0.38
     ofstream
    0.37
    Kraft
    0.37
     Heer
    0.37
    stripped
    0.37
     वस
    0.36
    hanahu
    0.36
     "~/
    0.36
     भारी
    0.36
    POSITIVE LOGITS
     agrupación
    0.44
     群
    0.40
    그룹
    0.39
    रु
    0.39
     gre
    0.38
     tracks
    0.38
    olutions
    0.38
    gruppen
    0.37
    ufen
    0.37
     processing
    0.36
    Activations Density 0.001%

    No Known Activations