© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140264
    Prev
    Next
    INDEX
    Explanations

    base reality

    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_12_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
    Sci
    0.40
    机的
    0.39
    िफाई
    0.39
    جري
    0.38
    تي
    0.38
     Fairfax
    0.37
     fáj
    0.37
     r
    0.37
    圾
    0.37
     जैसा
    0.36
    POSITIVE LOGITS
    ampil
    0.39
    ø
    0.39
     diferenças
    0.38
    ahiran
    0.38
    는
    0.37
    খানে
    0.37
     alguns
    0.37
    ções
    0.36
    enças
    0.36
     bokeh
    0.36
    Activations Density 0.005%

    No Known Activations