© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79177
    Prev
    Next
    INDEX
    Explanations

    inferiority or superiority

    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_0_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
    ד
    1.57
     ili
    1.42
    ב
    1.40
     oppure
    1.38
     ovvero
    1.34
     لأ
    1.33
     bude
    1.30
     vse
    1.29
     powinno
    1.29
    ພວກເຮົາ
    1.28
    POSITIVE LOGITS
    .
    1.94
    ного
    1.49
    ление
    1.38
    し
    1.28
    ль
    1.21
    ра
    1.18
    >
    1.15
    age
    1.14
    ald
    1.14
    ش
    1.13
    Activations Density 0.001%

    No Known Activations