© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33482
    Prev
    Next
    INDEX
    Explanations

    names ending in ian/az/ra/ri

    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_7_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
    '
    0.49
    <0x80>
    0.45
    )
    0.41
    </b>
    0.39
    <0x0D>
    0.37
    Message
    0.37
    </i>
    0.36
    </h2>
    0.34
    ↵
    0.34
    ),
    0.34
    POSITIVE LOGITS
    o
    0.49
    ।
    0.47
     courants
    0.46
     circunstancias
    0.43
    𝙤
    0.43
     élevés
    0.43
    alı
    0.42
    ா
    0.41
    𝐚
    0.41
    aş
    0.40
    Activations Density 0.005%

    No Known Activations