© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33599
    Prev
    Next
    INDEX
    Explanations

    but I can

    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
     چاندی
    0.39
    Pep
    0.37
    PEP
    0.37
    Aph
    0.36
    regarding
    0.36
    Bike
    0.35
    🐫
    0.35
    obranch
    0.35
    総
    0.35
    Provide
    0.34
    POSITIVE LOGITS
     exit
    0.39
     gesture
    0.39
     Mana
    0.39
     exits
    0.38
     zoom
    0.38
     measures
    0.37
     никто
    0.37
     しかし
    0.37
    МИ
    0.36
     din
    0.36
    Activations Density 0.001%

    No Known Activations