© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84859
    Prev
    Next
    INDEX
    Explanations

    gdscript

    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_23_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
    elerin
    0.35
    neider
    0.33
    obb
    0.33
    畕
    0.33
     সুল
    0.32
     boto
    0.32
    }}}
    0.32
     bivariate
    0.32
    \]
    0.31
    ivers
    0.31
    POSITIVE LOGITS
     jet
    0.38
     말미암
    0.35
    🫦
    0.34
     systèmes
    0.34
     مخطط
    0.34
    ्यूशन
    0.33
     mécanisme
    0.33
     molécules
    0.33
    殲
    0.33
     ট্যাব
    0.33
    Activations Density 0.000%

    No Known Activations