© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198636
    Prev
    Next
    INDEX
    Explanations

    letter or foo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     Schematic
    0.39
     Sche
    0.39
    まだ
    0.38
    ocalyptic
    0.37
    âncias
    0.36
     अभिकारक
    0.36
    ⃛
    0.35
    Execution
    0.35
    Variants
    0.35
    的大
    0.34
    POSITIVE LOGITS
     Châu
    0.42
     hopeless
    0.40
     educación
    0.40
     马
    0.40
     carnival
    0.39
     chooses
    0.38
     브랜드
    0.38
     hormone
    0.38
     communicates
    0.38
     trenger
    0.38
    Activations Density 0.000%

    No Known Activations