© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132314
    Prev
    Next
    INDEX
    Explanations

    likely to be

    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_6_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
    та
    1.23
    ли
    1.18
    é
    1.15
    al
    1.09
    I
    1.09
    і
    1.09
     т
    1.05
    স
    1.02
    то
    0.96
    ق
    0.96
    POSITIVE LOGITS
    ’
    0.98
    i
    0.92
     atk
    0.90
    That
    0.89
    Khokhlov
    0.89
    priv
    0.85
     legitim
    0.82
     Ditt
    0.82
    4
    0.82
    Prin
    0.81
    Activations Density 0.001%

    No Known Activations