© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139003
    Prev
    Next
    INDEX
    Explanations

    abide by, bound by

    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_12_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
    [_
    0.56
    ρίας
    0.56
     порядку
    0.56
    [
    0.55
    [(
    0.53
    lil
    0.53
    erina
    0.53
     झाल्यावर
    0.52
    lius
    0.52
    lir
    0.51
    POSITIVE LOGITS
     난
    0.53
    শিকান্ত
    0.52
    strcmp
    0.51
     decept
    0.51
     Elektro
    0.50
     කොට
    0.49
    ේ
    0.48
    ј
    0.48
    வற்ற
    0.47
    
    0.47
    Activations Density 0.000%

    No Known Activations