© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43737
    Prev
    Next
    INDEX
    Explanations

    you, to, good, Real

    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_13_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
     Cont
    0.35
    auche
    0.35
     Yi
    0.34
     Gute
    0.32
     उमेद
    0.32
     Feminist
    0.32
     }.
    0.31
     would
    0.31
     मुली
    0.31
     Nationale
    0.31
    POSITIVE LOGITS
    quantitative
    0.34
    million
    0.33
    ROLLER
    0.32
    三十
    0.32
    $
    0.31
    らの
    0.30
    cza
    0.30
    cubic
    0.30
    nonlinear
    0.30
     xxl
    0.29
    Activations Density 0.083%

    No Known Activations