© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171605
    Prev
    Next
    INDEX
    Explanations

    results confirming or indicating something

    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
    )}.
    0.45
     scar
    0.42
     Moran
    0.40
    b
    0.40
    is
    0.39
    😀
    0.39
    ind
    0.39
     Xan
    0.39
     Dessa
    0.39
     less
    0.38
    POSITIVE LOGITS
    잘
    0.52
    护理
    0.50
    שה
    0.49
     שה
    0.46
     Toxicology
    0.46
    기술
    0.46
    휘
    0.45
     सिलसिले
    0.45
     började
    0.44
    よ
    0.44
    Activations Density 0.000%

    No Known Activations