© 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. 68500
    Prev
    Next
    INDEX
    Explanations

    specific locations

    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
    South
    0.38
    শৃঙ্খলা
    0.37
     साउथ
    0.36
    леку
    0.36
     brig
    0.36
     redemption
    0.35
    *{
    0.35
     ಶಾ
    0.35
    接过
    0.35
     OPCODE
    0.35
    POSITIVE LOGITS
    ColorF
    0.42
     F
    0.42
    F
    0.40
     gpointer
    0.39
     Frem
    0.39
     gender
    0.38
    சிரியர்
    0.37
     Inns
    0.37
     biomarkers
    0.37
     cigars
    0.37
    Activations Density 0.001%

    No Known Activations