© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14987
    Prev
    Next
    INDEX
    Explanations

    code or instructions

    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_34_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
    汢
    0.39
     acab
    0.38
    睢
    0.37
    ული
    0.36
    炡
    0.36
    ultaneous
    0.36
    ijske
    0.36
    estay
    0.36
     ಸಂತ
    0.35
     adatt
    0.35
    POSITIVE LOGITS
     Executes
    0.36
     snacks
    0.34
    pytest
    0.33
    encers
    0.32
    コナ
    0.32
    此时
    0.32
     accolades
    0.32
    }',
    0.31
     accolade
    0.31
    forEach
    0.31
    Activations Density 0.011%

    No Known Activations