© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10909
    Prev
    Next
    INDEX
    Explanations

    infrasound

    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_13_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
    期货
    0.51
    lients
    0.50
    वेयर
    0.48
    ર્ટ
    0.47
    消费
    0.47
    穩
    0.47
    ApiException
    0.46
    Tried
    0.46
     philosophies
    0.46
    鵠
    0.46
    POSITIVE LOGITS
    המ
    0.64
    tetrahydro
    0.55
     SHRI
    0.55
    ा
    0.55
    mada
    0.54
    ческому
    0.53
    ास
    0.52
     टकराव
    0.52
    मिति
    0.51
    다
    0.50
    Activations Density 0.004%

    No Known Activations