© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138595
    Prev
    Next
    INDEX
    Explanations

    long-tail keywords

    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_37_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
    ObjectName
    0.43
    櫂
    0.40
     venues
    0.38
     সংখ্যা
    0.38
    ɩ
    0.38
     ACM
    0.38
     url
    0.38
     Mur
    0.38
    filename
    0.38
     број
    0.38
    POSITIVE LOGITS
    攔
    0.44
    拦截
    0.40
    拦
    0.40
    target
    0.39
    aturamento
    0.38
    渲
    0.38
    chini
    0.37
     targeting
    0.37
     Targeting
    0.36
    targeting
    0.36
    Activations Density 0.023%

    No Known Activations