© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    acts of prior sanction

    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
     lim
    0.21
    emie
    0.20
     poverty
    0.19
     Compet
    0.18
     الك
    0.18
    iras
    0.18
     باندې
    0.18
     e
    0.18
     Communic
    0.18
    "
    0.18
    POSITIVE LOGITS
     INDIA
    0.22
     DELHI
    0.22
     kerala
    0.22
     کنکریاں
    0.21
     ayurved
    0.21
    india
    0.21
    INDIA
    0.21
    鶉
    0.21
    Kerala
    0.21
     Gandhiji
    0.21
    Activations Density 0.005%

    No Known Activations