© 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. 90563
    Prev
    Next
    INDEX
    Explanations

    vision loss

    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
    e
    1.07
    ed
    0.71
    al
    0.66
    er
    0.65
    ev
    0.64
    alex
    0.61
    l
    0.59
    ein
    0.58
    f
    0.58
    y
    0.57
    POSITIVE LOGITS
     vineyards
    0.73
     powied
    0.64
    했
    0.63
     universes
    0.62
    ות
    0.62
    Ди
    0.61
    नि
    0.61
    Па
    0.61
    ！
    0.60
     viene
    0.59
    Activations Density 0.001%

    No Known Activations