© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45862
    Prev
    Next
    INDEX
    Explanations

    connecting or interconnected things

    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_13_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
    )$;
    0.46
    bajo
    0.43
    yeri
    0.43
     Ape
    0.40
     Sobre
    0.40
    )
    0.40
    esist
    0.39
    挝
    0.39
     compuesto
    0.39
    Ｅ
    0.39
    POSITIVE LOGITS
    棻
    0.45
    他们的
    0.44
    IUS
    0.44
     leurs
    0.43
     Thunderbolt
    0.42
     Dartmouth
    0.42
     uwagę
    0.42
    ман
    0.41
     їх
    0.41
     জ্ঞানের
    0.41
    Activations Density 0.037%

    No Known Activations