© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151610
    Prev
    Next
    INDEX
    Explanations

    rocky, loose terrain

    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_18_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
     Date
    0.45
     PUB
    0.44
     DUE
    0.44
    becomes
    0.43
     implies
    0.42
     Validator
    0.42
     p
    0.41
     DATE
    0.41
     "")
    0.41
     Dame
    0.41
    POSITIVE LOGITS
    महल
    0.49
     topaz
    0.47
    clav
    0.47
    પૂર્ણ
    0.46
    omány
    0.46
    鯤
    0.45
    ження
    0.45
    emt
    0.45
    MinIntensity
    0.45
    رك
    0.44
    Activations Density 0.000%

    No Known Activations