© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50230
    Prev
    Next
    INDEX
    Explanations

    everyday language

    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_30_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
     بارش
    0.27
     বির
    0.27
    ၾ
    0.26
    牥
    0.26
    Ē
    0.26
    统治
    0.25
     дзяржа
    0.24
    历
    0.24
     із
    0.23
     temporally
    0.23
    POSITIVE LOGITS
     misery
    0.26
     coursework
    0.25
    についての
    0.24
     forty
    0.24
    ibir
    0.24
    respective
    0.24
    க்கள்
    0.24
    this
    0.23
     recommendations
    0.23
     risult
    0.23
    Activations Density 0.022%

    No Known Activations