© 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. 42024
    Prev
    Next
    INDEX
    Explanations

    seasons the

    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
    ього
    0.46
     vídeos
    0.40
     фильмы
    0.38
     yaklaş
    0.38
    ]->
    0.38
     downregulation
    0.37
    Ư
    0.36
     kontrol
    0.36
     रेटिंग
    0.36
    /<
    0.36
    POSITIVE LOGITS
    shakespeare
    0.41
    UNESCO
    0.41
    合併
    0.39
    tke
    0.39
    合并
    0.38
    汇
    0.38
     Shakespeare
    0.38
     UNESCO
    0.38
     সাড়ে
    0.37
    Dylan
    0.36
    Activations Density 0.000%

    No Known Activations