© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236663
    Prev
    Next
    INDEX
    Explanations

    code tokens and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     Griechen
    0.22
     português
    0.21
     ف
    0.20
    infix
    0.20
     UCL
    0.20
     GSK
    0.20
     transmissão
    0.19
     Levante
    0.19
     frameworks
    0.19
     Entwicklung
    0.19
    POSITIVE LOGITS
    ombra
    0.25
    river
    0.22
     transcriptome
    0.22
     oftentimes
    0.22
    啡
    0.22
    ಮ್ಮೆ
    0.22
     forKey
    0.22
     checkFor
    0.22
    carrito
    0.21
    attup
    0.21
    Activations Density 0.045%

    No Known Activations