© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60999
    Prev
    Next
    INDEX
    Explanations

    MOSFET and oscillation frequency

    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_11_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
    ﺓ
    0.59
     क्‍
    0.52
     आंबेडकर
    0.52
     ہوگا
    0.51
    ᴺ
    0.51
     Ambrose
    0.49
     कष्ट
    0.49
    ﻯ
    0.49
    ؟
    0.49
    𝒟
    0.49
    POSITIVE LOGITS
    Phones
    0.52
    computers
    0.52
     kan
    0.51
    Boogie
    0.51
    Air
    0.51
    when
    0.50
    वली
    0.50
    Cuando
    0.50
    sberg
    0.50
    Aster
    0.50
    Activations Density 0.029%

    No Known Activations