© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143031
    Prev
    Next
    INDEX
    Explanations

    fog and clouds

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.40
    ╣
    0.40
     consec
    0.37
    λικ
    0.36
    鲷
    0.35
     Sasaki
    0.34
    UIC
    0.33
    dings
    0.33
    রায়
    0.33
    セイ
    0.33
    POSITIVE LOGITS
     fog
    2.72
    雾
    2.38
    Fog
    2.30
    fog
    2.28
     Fog
    2.27
     foggy
    2.25
    霧
    2.25
     cloud
    2.16
     clouds
    2.14
     mist
    2.03
    Activations Density 0.116%

    No Known Activations