© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 203995
    Prev
    Next
    INDEX
    Explanations

    put

    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
     undue
    0.46
     exces
    0.40
     popupButton
    0.40
     unduly
    0.39
     Pob
    0.37
     भर्ती
    0.35
    ը
    0.35
     naast
    0.35
     excessive
    0.35
     napis
    0.35
    POSITIVE LOGITS
     boarded
    0.42
    瞌
    0.41
     boredom
    0.40
     ding
    0.38
     nerd
    0.37
     missing
    0.37
    టై
    0.37
    觊
    0.37
    STRUCTURE
    0.36
    羡
    0.36
    Activations Density 0.001%

    No Known Activations