© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146829
    Prev
    Next
    INDEX
    Explanations

    foreign or unusual word

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Judge
    0.42
     anew
    0.38
    #
    0.37
     Judge
    0.36
     assent
    0.36
    judge
    0.36
    Mary
    0.35
     reparto
    0.34
    जों
    0.34
    뉴스
    0.33
    POSITIVE LOGITS
     endorsing
    0.48
    etaan
    0.44
    achelors
    0.41
    }}_
    0.40
    ંમે
    0.40
     специа
    0.39
     आम
    0.39
    ชั่น
    0.38
    ရောက်
    0.38
     =&
    0.38
    Activations Density 0.004%

    No Known Activations