© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195147
    Prev
    Next
    INDEX
    Explanations

    cypherpunk, evenings spent, chess

    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_15_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
    producing
    0.52
     Producing
    0.50
    ϊ
    0.49
     ($\
    0.48
     ($
    0.47
    phosphate
    0.46
     Produktion
    0.45
    image
    0.43
    pulse
    0.42
     Podcast
    0.42
    POSITIVE LOGITS
     বলা
    0.50
     sectarian
    0.49
     헤
    0.48
    ቖ
    0.47
    PUT
    0.46
    Cock
    0.46
    Checks
    0.45
     بک
    0.45
     চাও
    0.44
    ChatGPT
    0.44
    Activations Density 0.000%

    No Known Activations