© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89401
    Prev
    Next
    INDEX
    Explanations

    a, the, process

    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_23_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
    Cabin
    0.29
    污染
    0.29
    phen
    0.27
    Ƒ
    0.27
    cabin
    0.27
     buzz
    0.26
    geries
    0.26
    𝑄
    0.26
     cabin
    0.26
     Cabin
    0.26
    POSITIVE LOGITS
    )}_{
    0.30
    ല്ലോ
    0.30
     metade
    0.28
     Dua
    0.28
    ictionnaire
    0.28
     میشه
    0.28
     sb
    0.27
    )}
    0.27
     normalmente
    0.27
     然後
    0.26
    Activations Density 0.000%

    No Known Activations