© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145056
    Prev
    Next
    INDEX
    Explanations

    dishonorably, dishonor, dishonestly

    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
    ों
    1.48
    ્સ
    1.43
    د
    1.34
    𝓭
    1.31
    ม
    1.27
    s
    1.27
    স
    1.26
    տ
    1.25
    ку
    1.22
    ק
    1.22
    POSITIVE LOGITS
    at
    1.88
    an
    1.82
    1
    1.77
    8
    1.68
    7
    1.64
    for
    1.55
    ir
    1.52
    ous
    1.46
    на
    1.42
    9
    1.42
    Activations Density 0.000%

    No Known Activations