© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103751
    Prev
    Next
    INDEX
    Explanations

    B.Tech or FT related acronyms

    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_1_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
     první
    1.15
    ｒ
    1.09
    超過
    1.07
     =",
    1.05
     impossibile
    1.04
    。",
    1.02
     azione
    0.97
    }",
    0.96
    }']
    0.95
     odnosu
    0.95
    POSITIVE LOGITS
    es
    1.75
    s
    1.73
    M
    1.62
    D
    1.55
    4
    1.54
    3
    1.52
    ת
    1.50
    7
    1.48
    H
    1.45
    6
    1.44
    Activations Density 0.001%

    No Known Activations