© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14296
    Prev
    Next
    INDEX
    Explanations

    arena

    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_15_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
    Arvore
    0.47
     elegantly
    0.46
    ^{+}$
    0.46
     sitt
    0.45
    J
    0.45
    Alfa
    0.44
    Portugal
    0.44
    奕
    0.44
     ਅਤੇ
    0.44
    Elegant
    0.44
    POSITIVE LOGITS
    घे
    0.52
    uchos
    0.52
     potrzeby
    0.50
    恻
    0.50
     pelos
    0.47
     cursorPos
    0.47
    Validators
    0.47
     ставкалары
    0.47
     בפ
    0.46
    deleteAll
    0.46
    Activations Density 0.002%

    No Known Activations