© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230748
    Prev
    Next
    INDEX
    Explanations

    breakup

    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_6_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
    朳
    0.92
     effluents
    0.92
     Объ
    0.83
     않는
    0.83
    IsResolver
    0.83
     dilutions
    0.82
    एसआई
    0.80
    vasive
    0.80
    Ꭰ
    0.80
     机
    0.79
    POSITIVE LOGITS
    m
    1.39
    is
    1.37
    ai
    1.18
    f
    1.14
    <0x80>
    1.06
    st
    1.05
    ag
    1.03
    ad
    1.02
     for
    1.02
    g
    1.02
    Activations Density 0.000%

    No Known Activations