© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2598
    Prev
    Next
    INDEX
    Explanations

    robots and anime

    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_39_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
    asign
    0.37
     பொழுது
    0.37
    lhs
    0.35
    愫
    0.35
    Func
    0.33
    铨
    0.33
     penyeleng
    0.33
    }=\{
    0.32
    ജീ
    0.32
    ဳ
    0.32
    POSITIVE LOGITS
     Transformers
    0.57
     transformer
    0.52
     Transformer
    0.52
    Transformers
    0.50
     transformers
    0.47
    robot
    0.46
     cartoons
    0.45
    Transformer
    0.45
     комі
    0.43
    Robot
    0.42
    Activations Density 0.098%

    No Known Activations