© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53301
    Prev
    Next
    INDEX
    Explanations

    dependence

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     शत्र
    0.42
     периоди
    0.42
    🍼
    0.42
     periód
    0.41
    チョコレート
    0.41
    💵
    0.41
     значительно
    0.41
    adoles
    0.41
    䡈
    0.41
     расходов
    0.41
    POSITIVE LOGITS
     dependence
    0.54
     dependency
    0.45
     reliance
    0.44
     goodness
    0.43
    ங்கும்
    0.42
     Dependence
    0.42
     bounds
    0.41
     Listing
    0.41
     formal
    0.40
    穷
    0.40
    Activations Density 0.005%

    No Known Activations