© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13343
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     Gefahr
    0.42
     wypad
    0.42
    ﻅ
    0.40
    getState
    0.39
    ภัย
    0.39
     diffusion
    0.38
     getState
    0.38
    UTIONS
    0.38
     someday
    0.38
     जागा
    0.38
    POSITIVE LOGITS
    MLE
    0.45
     കീഴ
    0.42
    declaration
    0.38
    plac
    0.36
    !("{:
    0.36
     Monument
    0.36
     числен
    0.36
    டைந்த
    0.35
     মসজিদের
    0.35
    Interpretation
    0.35
    Activations Density 0.000%

    No Known Activations