© 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. 46216
    Prev
    Next
    INDEX
    Explanations

    healthy living and practices

    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
    um
    0.78
     silenced
    0.71
     malicious
    0.71
     lesión
    0.69
     bhij
    0.68
    ة
    0.66
     livré
    0.66
     vacío
    0.65
    ing
    0.65
    та
    0.64
    POSITIVE LOGITS
    S
    0.75
    G
    0.73
    option
    0.70
     t
    0.68
     त
    0.68
    TOF
    0.66
    D
    0.66
    RCT
    0.65
    T
    0.65
    ى
    0.65
    Activations Density 0.030%

    No Known Activations