© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179020
    Prev
    Next
    INDEX
    Explanations

    release()

    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_24_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
    piej
    0.38
     महाराज
    0.37
    ఖ్య
    0.37
    MAR
    0.36
    犸
    0.35
    Yves
    0.35
    DSP
    0.35
    ጥ
    0.35
    гл
    0.34
     सुरेंद्र
    0.34
    POSITIVE LOGITS
    iatric
    0.39
    áculos
    0.38
    様専用
    0.37
     Profiles
    0.37
    ບໍລິ
    0.37
     Frente
    0.36
    ুরু
    0.36
     जाया
    0.36
     बच्चों
    0.35
     compulsory
    0.35
    Activations Density 0.000%

    No Known Activations