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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38308
    Prev
    Next
    INDEX
    Explanations

    is there such a thing

    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_11_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
     năm
    0.66
     îns
    0.64
     т
    0.63
     stát
    0.63
    aków
    0.63
     настрой
    0.63
    äts
    0.63
     соль
    0.63
    𝐚
    0.62
    ак
    0.61
    POSITIVE LOGITS
    Y
    0.98
    G
    0.95
    Where
    0.91
    D
    0.88
    Aw
    0.87
    I
    0.86
    Beauty
    0.85
    Like
    0.85
    Deputy
    0.84
    Please
    0.83
    Activations Density 0.000%

    No Known Activations