© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125792
    Prev
    Next
    INDEX
    Explanations

    prostaglandin or prostate

    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
    ہ
    0.90
     azienda
    0.82
     investigación
    0.76
     indiqu
    0.76
     america
    0.76
     imprison
    0.75
     individualized
    0.75
     eldest
    0.75
     œuvres
    0.72
     americ
    0.72
    POSITIVE LOGITS
    as
    0.92
    a
    0.81
    q
    0.81
    o
    0.81
    av
    0.80
    う
    0.75
    ೮
    0.71
    ले
    0.68
    ᱘
    0.67
    an
    0.66
    Activations Density 0.001%

    No Known Activations