© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31929
    Prev
    Next
    INDEX
    Explanations

    start of turn markers

    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_40_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
    торин
    0.38
     Salmonella
    0.36
     नौकरियों
    0.36
    郯
    0.36
     დღ
    0.35
     cận
    0.35
     bepaalde
    0.35
    getTo
    0.35
    حياته
    0.35
     জীবের
    0.34
    POSITIVE LOGITS
     king
    0.40
     honestly
    0.39
     inputText
    0.37
     spi
    0.37
    绎
    0.36
    zl
    0.36
     fluent
    0.36
    ਜ਼
    0.36
     Bass
    0.35
    bass
    0.35
    Activations Density 0.026%

    No Known Activations