© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23354
    Prev
    Next
    INDEX
    Explanations

    think, expect, believe

    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_56_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
    Copyright
    0.35
    Rick
    0.35
    のかもし
    0.34
     avoided
    0.33
    Unlike
    0.32
    哇
    0.32
    Regardless
    0.32
    Ges
    0.32
    هرات
    0.32
    Brady
    0.31
    POSITIVE LOGITS
     생각
    1.91
    思った
    1.63
    予想
    1.59
    思
    1.57
    想像
    1.46
     예상
    1.45
     think
    1.30
    想象
    1.27
    Think
    1.22
    意
    1.22
    Activations Density 0.002%

    No Known Activations