© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24854
    Prev
    Next
    INDEX
    Explanations

    whichever

    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
    Negative Logits
     regardless
    0.53
    regardless
    0.43
     nie
    0.39
    ไม่
    0.38
    슴
    0.38
    不
    0.37
    orget
    0.36
    ô
    0.36
     ፍ
    0.35
     Nie
    0.35
    POSITIVE LOGITS
     whatever
    3.58
    whatever
    3.27
    Whatever
    3.25
     Whatever
    3.20
     whichever
    2.25
     whoever
    1.59
     apapun
    1.47
    atever
    1.28
    Whoever
    1.27
     Whoever
    1.26
    Activations Density 0.120%

    No Known Activations