© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181916
    Prev
    Next
    INDEX
    Explanations

    "else" followed by code blocks

    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_29_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
     Variations
    0.45
     канди
    0.41
     variations
    0.41
    碼
    0.40
     WHETHER
    0.39
     plötzlich
    0.38
     Subs
    0.37
    錫
    0.37
     În
    0.37
     effluent
    0.37
    POSITIVE LOGITS
    теры
    0.41
    四大
    0.40
    major
    0.40
    tel
    0.38
     buddy
    0.38
    racted
    0.37
     беско
    0.36
    atello
    0.36
     disgrace
    0.36
    SNS
    0.36
    Activations Density 0.001%

    No Known Activations