© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23717
    Prev
    Next
    INDEX
    Explanations

    "

    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_56_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
    ...)
    0.44
    ...”
    0.42
    äischen
    0.41
    릴
    0.41
     ...)
    0.40
    \"
    0.39
    expl
    0.38
    ...'
    0.38
     \%)$
    0.37
    édie
    0.37
    POSITIVE LOGITS
     m
    0.44
    𝑆
    0.42
     म
    0.38
    𝐽
    0.38
     ish
    0.37
    OutputType
    0.36
     Ambros
    0.36
     приблизи
    0.35
     Thrift
    0.34
     মাঝি
    0.33
    Activations Density 0.000%

    No Known Activations