© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35241
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
     Catal
    0.44
     Gue
    0.41
     Kingsley
    0.39
     Rom
    0.39
    Rom
    0.37
     CommandLine
    0.37
     Exo
    0.37
     G
    0.36
     rom
    0.36
    ɢ
    0.36
    POSITIVE LOGITS
     واب
    0.41
    وازن
    0.41
    Ahmed
    0.41
    vah
    0.40
     eb
    0.40
     ताजमहल
    0.40
    Ah
    0.39
    ABL
    0.38
    bbb
    0.38
     extractor
    0.38
    Activations Density 0.013%

    No Known Activations