© 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. 10024
    Prev
    Next
    INDEX
    Explanations

    root

    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
     آسیب
    0.72
     молодой
    0.67
     Justiça
    0.66
     молодых
    0.64
    is
    0.64
    <unused292>
    0.63
    ):["
    0.63
     Mesmo
    0.63
    𝓉
    0.63
    isAssignableFrom
    0.62
    POSITIVE LOGITS
     backlog
    0.59
    0.57
     vanity
    0.56
     rec
    0.51
     dial
    0.49
     archive
    0.48
     reg
    0.47
     buffet
    0.47
     code
    0.47
     hotel
    0.47
    Activations Density 0.075%

    No Known Activations