© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32425
    Prev
    Next
    INDEX
    Explanations

    equations and stories based

    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_40_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
     WARRANTY
    0.36
    蕎
    0.36
    öy
    0.35
    抽
    0.34
    cester
    0.33
    𝜁
    0.33
    osas
    0.33
    蜂
    0.33
    温泉
    0.32
     അമ
    0.32
    POSITIVE LOGITS
     based
    2.09
     Based
    1.88
    Based
    1.84
     BASED
    1.81
    based
    1.70
     berdasarkan
    1.70
    基于
    1.68
     dựa
    1.66
     basado
    1.64
     basé
    1.56
    Activations Density 0.257%

    No Known Activations