© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217122
    Prev
    Next
    INDEX
    Explanations

    forgiveness doesn't equal acceptance

    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_31_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
     lembut
    0.41
     сохранения
    0.38
     disclosed
    0.36
     trigger
    0.35
     hagy
    0.35
    autocon
    0.35
    垀
    0.35
    තාව
    0.35
     hed
    0.34
    ྃ
    0.34
    POSITIVE LOGITS
     imped
    0.43
     extravag
    0.40
     epidemics
    0.40
     perils
    0.40
     epidemic
    0.39
    ่า
    0.37
    épid
    0.36
     impediments
    0.36
    悪
    0.36
    막
    0.35
    Activations Density 0.003%

    No Known Activations