© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84347
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    াউন
    0.59
     contaminant
    0.59
    USION
    0.54
     transporter
    0.53
    的历史
    0.53
     อายุ
    0.53
    erà
    0.51
    )
    0.51
    蓣
    0.51
    蓥
    0.51
    POSITIVE LOGITS
    this
    0.62
    на
    0.60
    ן
    0.60
    ﺮ
    0.58
    rooms
    0.57
     abierta
    0.55
    و
    0.55
    ne
    0.54
    ܕ
    0.54
    dashed
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.