© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179577
    Prev
    Next
    INDEX
    Explanations

    conclusions from data

    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_24_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
     mas
    0.43
    *}$
    0.42
    സിൽ
    0.42
    imas
    0.41
    കൾ
    0.39
     nakon
    0.38
     samurai
    0.38
    🎻
    0.38
     <!--<
    0.38
    され
    0.38
    POSITIVE LOGITS
     Struct
    0.48
     Designer
    0.46
     Fountain
    0.43
     Franklin
    0.43
     Testing
    0.43
     Load
    0.43
     UML
    0.42
     Fashion
    0.42
     Pascal
    0.42
     Ziegler
    0.42
    Activations Density 0.000%

    No Known Activations