© 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. 14278
    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
    妊
    0.41
    vier
    0.39
    ateľ
    0.37
    ciąż
    0.37
    ruct
    0.37
    ⇆
    0.36
    folge
    0.36
     Vielen
    0.36
    ографи
    0.36
    MoveNext
    0.36
    POSITIVE LOGITS
     quotation
    0.39
     Jordan
    0.38
    扂
    0.38
     Eric
    0.38
     catapult
    0.38
     gur
    0.37
     Liss
    0.37
     quote
    0.36
    сное
    0.36
     সেন্টার
    0.36
    Activations Density 0.010%

    No Known Activations