© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149417
    Prev
    Next
    INDEX
    Explanations

    multi-language text

    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_59_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
    ờ
    0.47
    릿
    0.39
     multiple
    0.38
     upbringing
    0.37
     audio
    0.36
    ódigo
    0.36
     PSU
    0.35
     equation
    0.35
    UWORD
    0.34
     assessment
    0.34
    POSITIVE LOGITS
    Genus
    0.38
    धारी
    0.38
     Ran
    0.35
    gus
    0.35
     snorkel
    0.35
    achricht
    0.35
    ້
    0.35
     forg
    0.35
    Ran
    0.35
     cuadrados
    0.34
    Activations Density 0.010%

    No Known Activations