© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197544
    Prev
    Next
    INDEX
    Explanations

    Barbados flag

    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_9_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
    ih
    0.86
     in
    0.82
    ي
    0.81
     trajet
    0.70
    mat
    0.70
    i
    0.69
    ü
    0.69
    out
    0.68
    اد
    0.68
    ugs
    0.68
    POSITIVE LOGITS
    ków
    0.96
    માં
    0.90
    anın
    0.86
    Sensitive
    0.85
    Gov
    0.83
    S
    0.82
    Sock
    0.82
    kę
    0.81
    Bond
    0.80
    fruits
    0.80
    Activations Density 0.002%

    No Known Activations