© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150719
    Prev
    Next
    INDEX
    Explanations

    Clip, Esc, his, all

    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_18_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
    靱
    0.49
    )>
    0.48
     attributable
    0.48
    ">
    0.47
     misión
    0.46
    arias
    0.46
    )=>{
    0.45
     בין
    0.45
     Gobierno
    0.44
    rifice
    0.43
    POSITIVE LOGITS
    ब
    0.53
    ต
    0.52
    ก
    0.51
    Ᏸ
    0.49
     maiden
    0.48
    प
    0.48
    скім
    0.47
    ค
    0.47
    บ
    0.47
    тей
    0.46
    Activations Density 0.000%

    No Known Activations