© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207534
    Prev
    Next
    INDEX
    Explanations

    of phrase

    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_20_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
    /
    0.34
    ).
    0.33
     दार
    0.33
     Being
    0.33
    ">
    0.32
     Pod
    0.32
     быть
    0.32
    ),
    0.31
     ),
    0.31
    ých
    0.31
    POSITIVE LOGITS
    嘣
    0.39
    𒋾
    0.38
     geldiniz
    0.37
     vitth
    0.36
     muque
    0.36
     diagrama
    0.36
     nmea
    0.36
    والفقار
    0.36
     cromosoma
    0.35
    thisStudent
    0.34
    Activations Density 0.016%

    No Known Activations