© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198343
    Prev
    Next
    INDEX
    Explanations

    qualified, certified, trained

    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_15_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
     zwei
    0.30
    (
    0.28
    urados
    0.27
    ètres
    0.26
     Aero
    0.26
    La
    0.26
     Transfer
    0.25
     Kerja
    0.25
     Erfol
    0.25
     რამდენ
    0.25
    POSITIVE LOGITS
    终止
    0.27
     ڪري
    0.26
     সমস্ত
    0.25
    窒
    0.25
     ምስ
    0.24
    嘶
    0.24
     ทํา
    0.24
     trunc
    0.24
    マシン
    0.24
     coeffs
    0.24
    Activations Density 0.003%

    No Known Activations