© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212276
    Prev
    Next
    INDEX
    Explanations

    `ConvNet` or `library`

    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_5_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
    ਰ
    0.88
    ட்ட
    0.71
    。
    0.70
    리로
    0.69
    خدام
    0.68
    риев
    0.64
    暦
    0.62
    就
    0.61
     trein
    0.61
    рика
    0.60
    POSITIVE LOGITS
    a
    1.68
    d
    1.59
    t
    1.52
    s
    1.37
    m
    1.16
    f
    1.10
    st
    1.07
    di
    1.05
    r
    1.02
    ne
    1.01
    Activations Density 0.001%

    No Known Activations