© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249645
    Prev
    Next
    INDEX
    Explanations

    code and text

    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_56_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
    ཎ
    0.40
     unlike
    0.38
     Uzbekistan
    0.37
     +:+
    0.37
     Sa
    0.36
     объек
    0.36
     مام
    0.35
    涅
    0.35
     যেমন
    0.35
    URNING
    0.35
    POSITIVE LOGITS
    Will
    0.41
     எனக்கு
    0.38
    くらい
    0.38
    จ่าย
    0.38
    ก็จะ
    0.37
    Should
    0.36
    otiti
    0.36
    ething
    0.36
    has
    0.35
     facere
    0.35
    Activations Density 0.000%

    No Known Activations