© 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. 133563
    Prev
    Next
    INDEX
    Explanations

    plot

    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
    কেশন
    0.40
    ঞ্চিত
    0.38
    ஸுக்கு
    0.38
     Nob
    0.37
    CurrentImage
    0.36
    喰
    0.36
    rese
    0.35
     पार्वती
    0.35
     Identities
    0.34
    激素
    0.34
    POSITIVE LOGITS
     pathogen
    0.40
    ylle
    0.39
    Joh
    0.38
    soc
    0.37
     చే
    0.37
    zad
    0.37
    ś
    0.37
    HJ
    0.36
    zl
    0.36
     svar
    0.36
    Activations Density 0.001%

    No Known Activations