© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225833
    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_10_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
    ᅮ
    0.48
    ιν
    0.47
    to
    0.46
    歐
    0.46
     बतौर
    0.45
    atov
    0.45
    up
    0.45
     paci
    0.44
    า
    0.44
    ít
    0.44
    POSITIVE LOGITS
     are
    0.50
     Enrollment
    0.49
     graphing
    0.46
     spectrogram
    0.45
     (°
    0.43
     opposites
    0.42
     dite
    0.42
     treads
    0.41
     Admissions
    0.40
    نن
    0.40
    Activations Density 0.000%

    No Known Activations