© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203204
    Prev
    Next
    INDEX
    Explanations

    units of time

    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
     blur
    0.41
     εξε
    0.41
     `>=`,
    0.40
     ይጠ
    0.40
     pracuje
    0.39
     rotate
    0.39
     rotates
    0.39
     እንደሚ
    0.38
     مطلوب
    0.38
    పడుతుంది
    0.37
    POSITIVE LOGITS
     corresponded
    0.46
     vécu
    0.43
     lived
    0.42
     tended
    0.40
     vivió
    0.40
     Gave
    0.38
     oversaw
    0.38
    经历了
    0.38
    ﷻ
    0.37
    lived
    0.37
    Activations Density 0.004%

    No Known Activations