© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251340
    Prev
    Next
    INDEX
    Explanations

    marking

    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
     '('
    0.43
     массо
    0.42
     (\$
    0.41
     পরিত
    0.40
     mass
    0.40
     działalności
    0.40
    unya
    0.39
     (')
    0.39
     $(\
    0.38
     (£
    0.38
    POSITIVE LOGITS
    标记
    0.40
     அலுவ
    0.40
    提取
    0.40
    ibles
    0.38
     след
    0.37
     Addressing
    0.37
    抽取
    0.36
    )--
    0.36
    ヴァン
    0.35
     marking
    0.35
    Activations Density 0.001%

    No Known Activations