© 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. 143069
    Prev
    Next
    INDEX
    Explanations

    Can

    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
    Only
    0.44
     только
    0.43
     chỉ
    0.43
     seulement
    0.42
     sadece
    0.42
     only
    0.42
    only
    0.41
    只
    0.40
    defs
    0.40
     רק
    0.40
    POSITIVE LOGITS
     ఇందు
    0.43
    まった
    0.40
    萦
    0.38
     ocorreu
    0.38
    මෙ
    0.37
    enció
    0.37
     fnt
    0.37
    なった
    0.37
     occurred
    0.37
    expressed
    0.37
    Activations Density 0.005%

    No Known Activations