© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244032
    Prev
    Next
    INDEX
    Explanations

    pragma once, exception

    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_40_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
    説
    0.41
    摸
    0.41
    见面
    0.38
     गायब
    0.38
    πους
    0.38
     மாற
    0.37
    嚼
    0.37
    誘導
    0.36
    سى
    0.36
    Spot
    0.35
    POSITIVE LOGITS
    anio
    0.46
     orchestra
    0.41
     души
    0.39
    筍
    0.38
    ]#
    0.38
     transmisión
    0.38
    ácio
    0.37
    ilion
    0.36
    Mou
    0.36
     exhibits
    0.36
    Activations Density 0.000%

    No Known Activations