© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120619
    Prev
    Next
    INDEX
    Explanations

    list of positive outcomes

    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_27_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
    Соцмережа
    0.38
    ⇌
    0.35
     furnishes
    0.35
    zechoslovak
    0.35
    listed
    0.35
    ሖ
    0.34
    ➙
    0.34
    おそらく
    0.34
    ⋙
    0.34
    childNodes
    0.34
    POSITIVE LOGITS
     Linear
    0.38
     Quantification
    0.37
     Alp
    0.35
     Identifying
    0.35
     Dio
    0.34
     alp
    0.32
     решений
    0.32
     Consistency
    0.32
    㳑
    0.32
     G
    0.31
    Activations Density 0.009%

    No Known Activations