© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206309
    Prev
    Next
    INDEX
    Explanations

    greedy algorithms and approach

    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_19_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
     estimates
    0.53
     εξ
    0.47
     adolescents
    0.46
     Examine
    0.46
    ↵
    0.45
     Examining
    0.44
     Chunk
    0.44
     Ex
    0.44
     so
    0.43
    ଚ
    0.43
    POSITIVE LOGITS
    okol
    0.55
    owaniu
    0.48
    BtnPanel
    0.47
    وک
    0.46
    getMinimum
    0.46
    াধীন
    0.45
    environnement
    0.45
    ()!=
    0.44
    Alliance
    0.44
    entrop
    0.44
    Activations Density 0.000%

    No Known Activations