© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165399
    Prev
    Next
    INDEX
    Explanations

    testicles and vulgar expletives

    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_13_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
    ет
    0.57
    сса
    0.53
    сини
    0.52
    ложения
    0.51
    никами
    0.51
    الن
    0.50
    плы
    0.50
    پ
    0.49
    帑
    0.49
    нице
    0.48
    POSITIVE LOGITS
     servers
    0.58
     verified
    0.57
     who
    0.52
     KC
    0.52
     microwave
    0.50
     minions
    0.49
     expressed
    0.49
     confirmed
    0.48
     Verified
    0.47
     metal
    0.47
    Activations Density 0.000%

    No Known Activations