© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197525
    Prev
    Next
    INDEX
    Explanations

    roundup, cooling, español, arena

    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_15_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
     خواهد
    0.50
     perplex
    0.47
    lly
    0.47
     మీకు
    0.45
     craindre
    0.45
     willful
    0.44
    itie
    0.44
     థ
    0.43
    ahue
    0.43
    ie
    0.43
    POSITIVE LOGITS
    ﺘ
    0.55
    த்
    0.50
    権
    0.48
    ﻨ
    0.48
    ர்
    0.47
    EST
    0.47
    Β
    0.45
    نا
    0.45
    QC
    0.45
    노
    0.44
    Activations Density 0.000%

    No Known Activations