© 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. 178995
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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
    GGG
    0.37
     Winston
    0.36
     odv
    0.35
    +%
    0.35
     caul
    0.34
     boiling
    0.34
     xix
    0.34
    秵
    0.34
     \"%
    0.34
     Revival
    0.33
    POSITIVE LOGITS
    ेशनों
    0.43
    apadani
    0.42
    ocat
    0.42
    reno
    0.40
    ляции
    0.39
    Med
    0.38
    Threads
    0.38
    ColorBit
    0.38
    బాబు
    0.38
    je
    0.38
    Activations Density 0.000%

    No Known Activations