© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104515
    Prev
    Next
    INDEX
    Explanations

    instruction following or question answering

    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
    াদু
    0.40
     Bhand
    0.38
     sprout
    0.38
    ♥
    0.37
     Karlsson
    0.37
    wrapping
    0.36
    zad
    0.35
     følge
    0.35
     ایسا
    0.35
    velopper
    0.35
    POSITIVE LOGITS
    ｭ
    0.38
    सामाजिक
    0.38
    ändige
    0.38
    કા
    0.38
    REW
    0.36
    ändigen
    0.35
    顱
    0.35
    locationY
    0.35
    istatic
    0.35
    ственным
    0.34
    Activations Density 0.001%

    No Known Activations