© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219696
    Prev
    Next
    INDEX
    Explanations

    prime check

    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
     persisted
    0.42
    persist
    0.41
    ｈ
    0.37
     persuas
    0.37
     HINSTANCE
    0.37
     persist
    0.36
     pertin
    0.36
    toare
    0.36
    дель
    0.35
     persistence
    0.35
    POSITIVE LOGITS
    +"|
    0.42
    obenzene
    0.42
     योगदान
    0.38
    رد
    0.38
    +$
    0.38
     limit
    0.38
     Obec
    0.37
    极限
    0.37
    ক্ষ
    0.36
    productions
    0.36
    Activations Density 0.003%

    No Known Activations