© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206654
    Prev
    Next
    INDEX
    Explanations

    before

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    headed
    0.40
     चै
    0.38
    else
    0.38
    湾
    0.38
     간
    0.37
    保管
    0.37
    彙
    0.37
    šić
    0.37
    claimed
    0.36
    sigs
    0.36
    POSITIVE LOGITS
     retra
    0.42
     Carls
    0.41
     Pras
    0.39
     '../../../
    0.38
     each
    0.38
     ever
    0.38
     reproduce
    0.37
    ध्या
    0.37
     TAK
    0.37
     MCF
    0.37
    Activations Density 0.002%

    No Known Activations