© 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. 83512
    Prev
    Next
    INDEX
    Explanations

    potion

    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
    ного
    1.64
    </h3>
    1.48
    )
    1.47
    ación
    1.42
    ной
    1.41
    ные
    1.34
    ing
    1.31
    ется
    1.27
     that
    1.26
    ных
    1.24
    POSITIVE LOGITS
    на
    1.80
    ال
    1.71
    od
    1.60
    4
    1.60
    ak
    1.46
    8
    1.45
    7
    1.43
    ي
    1.43
    א
    1.43
    ot
    1.41
    Activations Density 0.001%

    No Known Activations