© 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. 242474
    Prev
    Next
    INDEX
    Explanations

    sets stores, allows, provides

    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
    含む
    0.56
    containing
    0.53
    Containing
    0.52
     containing
    0.49
    含
    0.48
     chứa
    0.46
     contenant
    0.46
     mengandung
    0.46
     Containing
    0.46
    包含了
    0.45
    POSITIVE LOGITS
     Template
    0.44
     templates
    0.40
    ದಿ
    0.40
    Template
    0.40
     Link
    0.39
     EDGE
    0.38
    庙
    0.38
     respiratory
    0.37
    Scalars
    0.37
     shadows
    0.37
    Activations Density 0.002%

    No Known Activations