© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94006
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    M
    1.02
     Ма
    0.54
    ME
    0.54
     l
    0.53
    MG
    0.52
    UP
    0.50
    MM
    0.50
    MS
    0.50
     Մ
    0.50
    ML
    0.48
    POSITIVE LOGITS
    K
    0.44
    F
    0.42
    Z
    0.39
    Й
    0.39
    })-
    0.38
     Shortcut
    0.37
    })-\
    0.37
    髀
    0.37
    Bl
    0.37
    ))-
    0.37
    Activations Density 0.004%

    No Known Activations