© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83240
    Prev
    Next
    INDEX
    Explanations

    dude

    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_0_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
    s
    1.82
    س
    1.72
    )
    1.61
    :
    1.48
    ی
    1.48
    с
    1.45
    ের
    1.42
    ă
    1.40
    ä
    1.34
    </h2>
    1.29
    POSITIVE LOGITS
    قي
    1.34
    Q
    1.24
    હાસ
    1.21
    东西
    1.20
    加え
    1.16
    1
    1.16
    E
    1.16
    Z
    1.13
    ৩
    1.13
    јединачна
    1.11
    Activations Density 0.000%

    No Known Activations