© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60821
    Prev
    Next
    INDEX
    Explanations

    personally identifiable information

    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_11_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
    ad
    0.81
     Er
    0.68
    nections
    0.65
    u
    0.65
     दिवस
    0.65
    wski
    0.64
    cipher
    0.64
    hive
    0.63
    fence
    0.62
    oncer
    0.62
    POSITIVE LOGITS
    <0xEA>
    0.59
    らす
    0.59
     teammates
    0.57
    ление
    0.55
     ath
    0.54
    На
    0.54
     côté
    0.53
     nuclé
    0.53
     culmin
    0.52
    ิล
    0.51
    Activations Density 0.001%

    No Known Activations