© 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. 163084
    Prev
    Next
    INDEX
    Explanations

    what does it mean

    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
    জী
    0.36
    Kayak
    0.35
     नक्की
    0.34
     byli
    0.34
    ︽
    0.34
    rax
    0.34
    ✔️
    0.33
    ync
    0.33
    حث
    0.33
    dayspecial
    0.33
    POSITIVE LOGITS
    予以
    0.42
     Larn
    0.40
    ন্থা
    0.40
     Gore
    0.39
     LB
    0.39
     owing
    0.39
    ȩ
    0.39
     Wong
    0.36
     Gug
    0.36
    écie
    0.36
    Activations Density 0.001%

    No Known Activations