© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158824
    Prev
    Next
    INDEX
    Explanations

    turned out

    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_2_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
    1.52
    ться
    1.49
    ar
    1.48
    el
    1.33
    ே
    1.30
    et
    1.23
    Date
    1.23
    in
    1.21
    ె
    1.18
    ار
    1.17
    POSITIVE LOGITS
    )
    1.27
    在
    1.10
    是为了
    1.06
    0
    1.05
     buzzing
    1.03
    ำ
    1.02
     a
    0.99
    ও
    0.98
    是要
    0.96
     QLabel
    0.96
    Activations Density 0.000%

    No Known Activations