© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156739
    Prev
    Next
    INDEX
    Explanations

    yielding or giving

    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_2_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
    ية
    1.75
    ة
    1.68
    ك
    1.41
    ק
    1.37
    した
    1.28
    ing
    1.26
    ने
    1.25
    O
    1.25
     excite
    1.23
    V
    1.23
    POSITIVE LOGITS
    x
    1.23
    has
    1.18
     reasoned
    1.11
     Controvers
    1.08
     পরও
    1.05
     Types
    1.03
     Usual
    1.02
     Contracts
    0.98
     HAS
    0.97
     Vegetation
    0.96
    Activations Density 0.000%

    No Known Activations