© 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. 138598
    Prev
    Next
    INDEX
    Explanations

    Slovenia Ljubljana

    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
    ニコ
    0.41
    क्शंस
    0.40
    ニス
    0.40
    occu
    0.40
    尼
    0.38
     loaded
    0.37
    никах
    0.36
     시장
    0.36
     অমিত
    0.36
    ニ
    0.36
    POSITIVE LOGITS
     Union
    0.40
    Union
    0.39
     Tres
    0.38
    Hall
    0.38
     Hall
    0.38
     Acts
    0.37
    ሆን
    0.37
     akt
    0.36
    TrackAngle
    0.36
     Bres
    0.35
    Activations Density 0.001%

    No Known Activations