© 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. 203131
    Prev
    Next
    INDEX
    Explanations

    mention of sickness

    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
    k
    1.27
    2
    1.24
    _
    1.23
    य
    1.18
     illnesses
    1.12
    ;
    1.07
    ק
    1.05
    ہ
    1.05
    genic
    1.02
    gi
    1.02
    POSITIVE LOGITS
    as
    1.12
     غير
    1.06
     mít
    1.03
    ير
    1.02
     comenzó
    1.02
     Burada
    1.00
    asının
    1.00
     سي
    0.99
     compré
    0.99
    هاي
    0.98
    Activations Density 0.002%

    No Known Activations