© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177981
    Prev
    Next
    INDEX
    Explanations

    fractions or ratios

    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_29_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
     கதை
    0.41
    续
    0.39
     Impacts
    0.38
    䐪
    0.38
    IPP
    0.38
    典
    0.38
     कहानी
    0.37
    ใหญ
    0.37
     großes
    0.37
    ppy
    0.37
    POSITIVE LOGITS
    ಚಾರ
    0.38
    lambda
    0.36
    abcdef
    0.36
     createWindow
    0.35
     provider
    0.35
     locator
    0.34
    vanishing
    0.34
     lambda
    0.33
    娇
    0.33
     Nam
    0.33
    Activations Density 0.000%

    No Known Activations