© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157098
    Prev
    Next
    INDEX
    Explanations

    specific entities and items

    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_50_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
     Haus
    0.39
     pensiero
    0.39
     ケ
    0.38
     케
    0.38
    Strike
    0.37
    :][
    0.36
     דו
    0.36
     downtime
    0.36
     kneel
    0.36
     अश्व
    0.36
    POSITIVE LOGITS
     cock
    0.41
    ball
    0.38
    Cock
    0.37
    érus
    0.37
    Combination
    0.37
    Allocation
    0.36
    崞
    0.36
    Benz
    0.35
    榕
    0.35
    ISTS
    0.35
    Activations Density 0.018%

    No Known Activations