© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    weather and seasons

    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_40_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
     Evolutionary
    0.39
     Aval
    0.38
     internationales
    0.38
    ㄻ
    0.37
     cima
    0.36
     Spend
    0.35
     internacionais
    0.35
     বিল
    0.35
     diritti
    0.35
    𒄿
    0.35
    POSITIVE LOGITS
     warmer
    2.05
     colder
    1.58
     warm
    1.52
    warm
    1.35
    Warm
    1.34
     warme
    1.24
     Warm
    1.21
     cooler
    1.20
    暖かい
    1.17
     warmest
    1.12
    Activations Density 0.058%

    No Known Activations