© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218632
    Prev
    Next
    INDEX
    Explanations

    look

    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_47_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
    bases
    0.40
     ž
    0.37
     워
    0.37
    WA
    0.36
     poč
    0.35
     ordinary
    0.35
    arith
    0.35
     Strip
    0.34
    alet
    0.34
    ꒱
    0.34
    POSITIVE LOGITS
    𐰃
    0.43
    యో
    0.42
     تربيع
    0.42
    ިޔ
    0.40
    AMENTO
    0.40
    సం
    0.39
     ڪري
    0.39
     আস
    0.39
    __|
    0.39
     reticulum
    0.39
    Activations Density 0.001%

    No Known Activations