© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14966
    Prev
    Next
    INDEX
    Explanations

    study area or topic

    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_40_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
     boosting
    0.38
     poppy
    0.36
     dysph
    0.36
     kamb
    0.36
    tonic
    0.35
    ায়ন
    0.35
    ંટણી
    0.35
    鲶
    0.34
     terl
    0.33
    ちに
    0.33
    POSITIVE LOGITS
     study
    1.87
     Study
    1.79
    Study
    1.78
    study
    1.76
     STUDY
    1.59
     estudio
    1.46
     estudo
    1.39
     स्टडी
    1.38
     studie
    1.32
     अध्ययन
    1.30
    Activations Density 0.032%

    No Known Activations