© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175348
    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_24_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
     AUT
    0.37
    ⌣
    0.36
     Validación
    0.36
    ೂರ್ವ
    0.35
    稳定
    0.35
    賃
    0.35
     contribution
    0.34
     prog
    0.34
     endorsed
    0.34
     izin
    0.34
    POSITIVE LOGITS
    atanam
    0.43
     języ
    0.41
    接待
    0.40
    lox
    0.40
    🤪
    0.39
    ùm
    0.39
    țe
    0.38
    ofstream
    0.38
    intaan
    0.38
     wre
    0.38
    Activations Density 0.000%

    No Known Activations