© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6628
    Prev
    Next
    INDEX
    Explanations

    conference, website, or programming links

    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_39_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
     схо
    0.35
     특별
    0.34
    Intersect
    0.34
    iteritems
    0.33
     tessel
    0.33
    ▃
    0.33
    Testables
    0.33
    ากหลาย
    0.33
     hautes
    0.32
    riterion
    0.32
    POSITIVE LOGITS
    忘
    0.45
     menulis
    0.41
     அட்ட
    0.40
     реєстра
    0.38
    endaftaran
    0.38
    adani
    0.38
     startActivity
    0.37
    दारा
    0.37
    ディション
    0.37
     पुस्तिका
    0.37
    Activations Density 0.024%

    No Known Activations