© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74904
    Prev
    Next
    INDEX
    Explanations

    and gotten

    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_31_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
    aksanakan
    0.47
    很有
    0.38
    홧
    0.38
     done
    0.38
    इज
    0.37
     ऑलरेडी
    0.37
     witnessed
    0.36
    ("+
    0.36
    了这个
    0.35
     بالفعل
    0.35
    POSITIVE LOGITS
    擞
    0.39
    nich
    0.38
    unsqueeze
    0.38
    tern
    0.33
    Gold
    0.33
     nix
    0.33
    涅
    0.33
     সঙ্ক
    0.32
     ahor
    0.32
    lação
    0.32
    Activations Density 0.033%

    No Known Activations