© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42905
    Prev
    Next
    INDEX
    Explanations

    `@page`, `selector`, `@Test`

    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_3_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
    is
    0.83
    or
    0.81
    é
    0.78
    ens
    0.71
    IAN
    0.71
    ess
    0.70
    lara
    0.70
     व
    0.70
    ен
    0.70
     осуществ
    0.67
    POSITIVE LOGITS
    “
    0.78
    "
    0.74
    Ι
    0.73
    บ
    0.68
    真
    0.68
    红
    0.66
    }$
    0.66
    ið
    0.66
    因为
    0.64
    名
    0.64
    Activations Density 0.002%

    No Known Activations