© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130960
    Prev
    Next
    INDEX
    Explanations

    effects or implications

    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_50_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
    聚
    0.62
     condensation
    0.54
     condensing
    0.53
     gathering
    0.50
     condensed
    0.47
     coag
    0.47
    ưng
    0.47
     tụ
    0.46
     condense
    0.46
    汇
    0.46
    POSITIVE LOGITS
    带
    0.42
    帶
    0.41
    gens
    0.38
     取っ
    0.38
    take
    0.38
    ícia
    0.37
     带
    0.36
    ➀
    0.36
     ござい
    0.36
     Pont
    0.36
    Activations Density 0.001%

    No Known Activations