© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66419
    Prev
    Next
    INDEX
    Explanations

    Enhanced protection

    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_41_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
     Broward
    0.41
     billing
    0.39
     हृदया
    0.38
    舛
    0.38
    Brazilian
    0.38
     veter
    0.37
     Available
    0.37
    Billing
    0.36
    igger
    0.36
     emerged
    0.36
    POSITIVE LOGITS
     pea
    0.74
     peas
    0.71
     Pea
    0.64
    peas
    0.59
    豌
    0.54
     Peas
    0.52
    pea
    0.50
    arist
    0.39
     मटर
    0.38
     알파
    0.37
    Activations Density 0.002%

    No Known Activations