© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237731
    Prev
    Next
    INDEX
    Explanations

    Nasdaq direction

    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_32_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
    সিদ্ধ
    0.34
    ின்றது
    0.33
    ার্থীর
    0.33
     অস্থির
    0.32
     visually
    0.30
    Sund
    0.30
    覦
    0.30
    visually
    0.29
    ḿ
    0.29
    仇
    0.29
    POSITIVE LOGITS
     )}
    0.34
     Finn
    0.30
     Expires
    0.30
     Enroll
    0.29
     tama
    0.29
     Payable
    0.29
    农
    0.29
     ನೇ
    0.29
     تاس
    0.29
    วิน
    0.28
    Activations Density 0.107%

    No Known Activations