© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48873
    Prev
    Next
    INDEX
    Explanations

    as

    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_55_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
    Well
    2.14
     Well
    2.03
    WELL
    2.02
     WELL
    1.97
    well
    1.93
    Wells
    1.90
    wells
    1.86
    井
    1.81
     Wells
    1.75
     wells
    1.71
    POSITIVE LOGITS
     tiens
    0.40
     discovered
    0.36
    一座
    0.36
     मुस्क
    0.36
     braiding
    0.35
     trao
    0.35
     dirty
    0.35
    素敵な
    0.35
     eosin
    0.34
     Squ
    0.34
    Activations Density 0.004%

    No Known Activations