© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63281
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind's brain

    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_41_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
     metres
    0.38
    ixels
    0.37
    雾
    0.36
     압
    0.36
    mma
    0.35
    пут
    0.35
    মিত
    0.35
     возду
    0.35
    xp
    0.34
    ayv
    0.34
    POSITIVE LOGITS
    brain
    0.89
     brain
    0.88
    Brain
    0.82
     Brain
    0.82
    脑
    0.70
     ब्रेन
    0.70
    脳
    0.68
    腦
    0.66
     brains
    0.65
    brains
    0.61
    Activations Density 0.012%

    No Known Activations