© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39513
    Prev
    Next
    INDEX
    Explanations

    Arpad Elo

    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_3_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
    a
    0.88
    us
    0.69
    de
    0.65
    ).
    0.63
    al
    0.62
    me
    0.61
    ding
    0.61
    se
    0.59
    )
    0.58
    Imidazole
    0.57
    POSITIVE LOGITS
    िस
    0.69
    িক
    0.64
    एस
    0.60
    MC
    0.58
    าน
    0.57
    kowej
    0.57
    ка
    0.56
    スメ
    0.56
     spolu
    0.56
     âgé
    0.55
    Activations Density 0.010%

    No Known Activations