© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122839
    Prev
    Next
    INDEX
    Explanations

    wheel objects

    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_3_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
    ש
    0.62
    uk
    0.59
    רו
    0.59
     $
    0.59
    مان
    0.58
     that
    0.58
    য়োজনীয়
    0.57
     que
    0.56
    Minimize
    0.56
     dass
    0.54
    POSITIVE LOGITS
     ruedas
    0.76
    轮
    0.72
     wheels
    0.68
    (
    0.68
    fic
    0.67
    wheel
    0.66
     élections
    0.64
     уви
    0.63
     wheeled
    0.63
    wheeled
    0.63
    Activations Density 0.000%

    No Known Activations