© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132051
    Prev
    Next
    INDEX
    Explanations

    time format hh:mm:ss

    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_1_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
    ing
    1.95
    and
    1.73
    ad
    1.38
    at
    1.31
    ة
    1.31
    E
    1.19
    O
    1.19
    는
    1.17
    0
    1.16
    아
    1.16
    POSITIVE LOGITS
    ).
    0.98
    sembles
    0.95
    }.
    0.88
    punkt
    0.88
     doux
    0.83
     religieux
    0.81
     शकतात
    0.80
    tes
    0.79
    dai
    0.78
    ttä
    0.78
    Activations Density 0.002%

    No Known Activations