© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4841
    Prev
    Next
    INDEX
    Explanations

    reboot nation links

    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_39_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
    bmod
    0.36
    stwa
    0.35
    ็น
    0.35
    édération
    0.34
     modList
    0.34
    तेश
    0.34
     Peña
    0.34
    ञ
    0.34
    緖
    0.34
    线条
    0.33
    POSITIVE LOGITS
    Stretch
    0.42
     stretch
    0.38
     забу
    0.38
     Stretch
    0.38
     descom
    0.37
    Dist
    0.36
     desarrollan
    0.36
    Unlock
    0.36
    манов
    0.35
     Dist
    0.35
    Activations Density 0.049%

    No Known Activations