© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69480
    Prev
    Next
    INDEX
    Explanations

    frost

    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_46_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
    mena
    0.40
    isors
    0.39
     glass
    0.38
    glass
    0.38
    Glass
    0.37
     pariet
    0.37
    owna
    0.37
    zoic
    0.37
    asmussen
    0.36
    㙂
    0.36
    POSITIVE LOGITS
     frost
    1.65
     Frost
    1.52
    Frost
    1.50
     frosted
    1.42
    frost
    1.39
     frosty
    1.32
     frosts
    1.25
    Fro
    1.23
     Fro
    1.23
     frosting
    1.20
    Activations Density 0.053%

    No Known Activations