© 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. 9380
    Prev
    Next
    INDEX
    Explanations

    if not, absolutely not

    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
    ہد
    0.40
    很简单
    0.40
    ichloro
    0.39
    哦
    0.38
     กล่าว
    0.37
     Brion
    0.37
    τές
    0.36
     করেই
    0.36
    嚯
    0.35
     ANZ
    0.35
    POSITIVE LOGITS
     not
    2.05
    not
    1.83
    Not
    1.51
     NOT
    1.48
    NOT
    1.44
     Not
    1.34
     όχι
    1.29
    不仅
    1.08
    不僅
    1.04
     नॉट
    0.91
    Activations Density 0.062%

    No Known Activations