© 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. 202353
    Prev
    Next
    INDEX
    Explanations

    well

    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
    Implementing
    0.41
    ಟ್ರ
    0.40
    IMPLEMENT
    0.40
     چاہیے۔
    0.39
     საჭ
    0.38
     ಶಿ
    0.38
    Implementation
    0.38
    帷
    0.38
    implementation
    0.38
    Designing
    0.37
    POSITIVE LOGITS
     geschrieben
    0.61
     scritto
    0.58
     kirjo
    0.55
     write
    0.54
     written
    0.52
     menulis
    0.50
     wrote
    0.49
     écrit
    0.49
     ditulis
    0.48
     escrito
    0.47
    Activations Density 0.002%

    No Known Activations