© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260919
    Prev
    Next
    INDEX
    Explanations

    the/an followed by noun

    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_22_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
    (',
    0.39
     calyce
    0.39
     dashes
    0.37
    вому
    0.37
    秒
    0.37
     Konto
    0.36
    ఎఫ్
    0.36
     зро
    0.36
     titik
    0.35
     -------------
    0.34
    POSITIVE LOGITS
    ículos
    0.44
    面的
    0.40
     Mixtures
    0.40
    ধি
    0.39
     Chlor
    0.39
    icultura
    0.38
    ">(
    0.38
    uminum
    0.38
    igment
    0.37
    ologia
    0.37
    Activations Density 0.003%

    No Known Activations