© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77163
    Prev
    Next
    INDEX
    Explanations

    conclusion methods

    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
     Revolutionary
    0.35
     Aquatic
    0.32
    嫦
    0.32
     IDC
    0.32
     சுமார்
    0.31
    Agar
    0.31
    糠
    0.31
    自觉
    0.31
     Estoy
    0.30
     заранее
    0.30
    POSITIVE LOGITS
    гле
    0.36
     rę
    0.34
     worn
    0.33
     row
    0.33
     pangan
    0.33
    älfte
    0.33
     lith
    0.32
     bölümde
    0.32
    行
    0.31
     tiet
    0.31
    Activations Density 0.000%

    No Known Activations