© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45673
    Prev
    Next
    INDEX
    Explanations

    climate descriptions

    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_22_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
    鸵
    0.45
    贋
    0.44
     tekn
    0.44
    első
    0.42
     প্রয
    0.42
    hasClass
    0.42
     hänen
    0.42
    maßnahmen
    0.41
     gafas
    0.41
     সরাস
    0.41
    POSITIVE LOGITS
    ces
    0.42
    spring
    0.40
    cest
    0.38
    分析
    0.38
    ouve
    0.37
     Ceres
    0.37
    哼
    0.37
     Operational
    0.37
     кре
    0.36
     cy
    0.36
    Activations Density 0.005%

    No Known Activations