© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170803
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    erialize
    0.40
    )])
    0.39
     ನಾವು
    0.38
    姆斯
    0.38
     $($
    0.37
     dimensi
    0.37
     –
    0.36
    )=$
    0.36
     $)$
    0.36
    )–
    0.36
    POSITIVE LOGITS
    ्यून
    0.38
    점에서
    0.37
    ---
    0.36
    --
    0.36
    좋
    0.36
    possible
    0.36
    Train
    0.35
    weekly
    0.35
    <0xC2>
    0.35
     weekly
    0.35
    Activations Density 0.014%

    No Known Activations