© 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. 202777
    Prev
    Next
    INDEX
    Explanations

    cutting materials

    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
    㫣
    0.40
     ਦਾ
    0.37
     taill
    0.37
    netty
    0.36
    Botan
    0.35
     מו
    0.35
    植
    0.35
     pukul
    0.34
     Botan
    0.34
     κατα
    0.34
    POSITIVE LOGITS
    Boards
    0.44
     रिक्
    0.40
     amour
    0.40
     bargains
    0.40
     love
    0.40
     lovers
    0.38
     Boards
    0.38
     boards
    0.37
     knives
    0.37
    板
    0.37
    Activations Density 0.002%

    No Known Activations