© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5647
    Prev
    Next
    INDEX
    Explanations

    code and logic

    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_44_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
     Decatur
    0.44
     dài
    0.43
     दिसम्बर
    0.43
     December
    0.42
    ڊ
    0.40
    Kar
    0.40
    ঙ্গের
    0.38
     καλ
    0.38
     Kar
    0.37
    December
    0.36
    POSITIVE LOGITS
     CPD
    0.43
     आइक
    0.38
    ivati
    0.37
    roskop
    0.37
    сс
    0.37
    ;";
    0.37
     qs
    0.37
    ಂಕ್
    0.37
    incipal
    0.36
     centrif
    0.36
    Activations Density 0.001%

    No Known Activations