© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121315
    Prev
    Next
    INDEX
    Explanations

    declutter

    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_37_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
    rases
    0.45
    Heap
    0.44
     heaped
    0.42
     pile
    0.41
    heap
    0.41
    pile
    0.41
    堆
    0.41
    storage
    0.40
    Pile
    0.40
    PILE
    0.39
    POSITIVE LOGITS
    いたい
    0.40
     DEC
    0.39
     →
    0.39
     GK
    0.38
     実
    0.38
    点头
    0.38
    Gamma
    0.37
     Development
    0.36
     Reuse
    0.36
    →
    0.36
    Activations Density 0.007%

    No Known Activations