© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10442
    Prev
    Next
    INDEX
    Explanations

    microSD card

    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_13_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
    ArgsConstructor
    0.49
    АС
    0.48
    АР
    0.47
     빅뱅
    0.47
    กล
    0.46
    ಗಿ
    0.46
    Ủ
    0.46
    ﺯ
    0.45
     விசாரணை
    0.45
    ETER
    0.44
    POSITIVE LOGITS
    tabname
    0.51
     realizzare
    0.51
     venden
    0.49
     ತುಂಬ
    0.48
    antad
    0.48
    टामिन
    0.48
     табле
    0.48
    et
    0.46
     Perrin
    0.46
    to
    0.46
    Activations Density 0.002%

    No Known Activations