© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196833
    Prev
    Next
    INDEX
    Explanations

    dangerous and motors

    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_4_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
     erős
    0.53
     vă
    0.51
    ได้รับการ
    0.49
     Pigs
    0.48
    蟶
    0.48
    ییر
    0.46
     glittering
    0.46
     argomento
    0.46
     Jahren
    0.45
    ِی
    0.45
    POSITIVE LOGITS
    it
    0.50
    and
    0.49
    w
    0.47
    a
    0.46
    ona
    0.45
    ar
    0.44
    ت
    0.44
    ul
    0.43
    qu
    0.42
    ane
    0.41
    Activations Density 0.002%

    No Known Activations