© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211461
    Prev
    Next
    INDEX
    Explanations

    indeed

    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_5_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
     основ
    0.88
     הע
    0.88
     quem
    0.86
     де
    0.85
     σε
    0.84
     leden
    0.82
     จึง
    0.81
    k
    0.81
     لیګ
    0.80
     seguenti
    0.79
    POSITIVE LOGITS
    ä
    1.83
    ag
    1.41
    (
    1.24
    ens
    1.20
    us
    1.15
    리
    1.15
    RI
    1.05
    مة
    1.05
    ari
    1.02
     on
    0.99
    Activations Density 0.000%

    No Known Activations