© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44837
    Prev
    Next
    INDEX
    Explanations

    SSH keys and file operations

    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_13_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
    いても
    0.50
    ་
    0.48
    ítulo
    0.48
     औद्योगिक
    0.48
     investigador
    0.47
    nes
    0.46
    industrial
    0.46
    νας
    0.46
    Irish
    0.46
    ät
    0.45
    POSITIVE LOGITS
     FAQ
    0.46
     c
    0.44
     collinear
    0.44
     medium
    0.43
     can
    0.43
     respons
    0.43
     stabilizer
    0.43
    рактеристики
    0.43
     Tier
    0.42
     lifeline
    0.41
    Activations Density 0.000%

    No Known Activations