© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89283
    Prev
    Next
    INDEX
    Explanations

    grasp

    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_60_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
     Gr
    0.92
    G
    0.89
    Gr
    0.59
     Г
    0.57
    Ｇ
    0.47
    つ
    0.46
    Г
    0.45
    緊
    0.45
    紧
    0.45
     firm
    0.43
    POSITIVE LOGITS
     grasp
    2.38
     grasping
    2.33
     grasped
    2.31
    grasp
    2.02
     gras
    1.90
     nắm
    1.67
    把握
    1.55
    gras
    1.44
     Gras
    1.29
    掌握
    1.09
    Activations Density 0.001%

    No Known Activations