© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176064
    Prev
    Next
    INDEX
    Explanations

    1900s-2000s

    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_24_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
    今後
    0.42
    これからも
    0.39
     ниж
    0.39
    씨
    0.38
    ու
    0.38
    يش
    0.37
     enth
    0.36
     спів
    0.36
     Beech
    0.36
     filmmaking
    0.36
    POSITIVE LOGITS
    计数
    0.40
    kv
    0.38
     timestep
    0.37
     Galbraith
    0.36
     tertentu
    0.36
    logistic
    0.36
     století
    0.35
    learned
    0.35
    둣
    0.34
    ړ
    0.34
    Activations Density 0.001%

    No Known Activations