© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116225
    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_27_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
     B
    0.41
     Ph
    0.40
     hail
    0.38
    Ph
    0.37
     साइ
    0.37
    A
    0.37
    燒
    0.37
     Give
    0.37
    进
    0.37
     if
    0.36
    POSITIVE LOGITS
    atchewan
    0.49
    🦒
    0.46
    стояния
    0.45
    RequestMapping
    0.44
    рактеристики
    0.42
    ૄ
    0.42
    েরিক
    0.42
     vinho
    0.42
    evice
    0.41
    👠
    0.41
    Activations Density 0.000%

    No Known Activations