© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207368
    Prev
    Next
    INDEX
    Explanations

    upside

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Rub
    0.37
    ანი
    0.37
    clr
    0.36
     đặt
    0.36
    كن
    0.36
    rub
    0.35
    nee
    0.35
     ܕ
    0.35
    isnan
    0.35
    ni
    0.35
    POSITIVE LOGITS
     upside
    3.05
     downside
    2.73
     Ups
    1.84
    Ups
    1.80
     downsides
    1.76
    ups
    1.48
     drawback
    1.47
     ups
    1.44
     UPS
    1.23
    UPS
    1.21
    Activations Density 0.085%

    No Known Activations