© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176887
    Prev
    Next
    INDEX
    Explanations

    inventories due, prison

    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_24_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
    原则
    0.45
    ᒎ
    0.43
    ಬ್ಬಿಣ
    0.43
    Ꮦ
    0.42
    지는
    0.39
    Вот
    0.39
     बुन्देलखण्ड
    0.39
     Amherst
    0.39
     NONE
    0.38
    椛
    0.38
    POSITIVE LOGITS
    coal
    0.45
    Sweet
    0.44
    loyd
    0.42
    ijks
    0.42
    áp
    0.41
    volving
    0.41
    kyl
    0.41
    ijker
    0.41
    grid
    0.40
    ÿ
    0.40
    Activations Density 0.000%

    No Known Activations