© 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. 204174
    Prev
    Next
    INDEX
    Explanations

    perfectly + adjective/verb

    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
     as
    1.16
     on
    1.09
     I
    0.96
     اوقات
    0.91
    í
    0.88
    い
    0.88
    大
    0.87
    お金
    0.86
     attiv
    0.83
     include
    0.83
    POSITIVE LOGITS
    i
    1.02
    ARE
    0.90
    ın
    0.89
    u
    0.86
    ן
    0.83
    <0x80>
    0.83
    ți
    0.82
    কে
    0.77
    :
    0.76
    ção
    0.76
    Activations Density 0.000%

    No Known Activations