© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    Google Deep

    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
    年轻
    0.41
     relatively
    0.40
     অভিষেক
    0.39
    较
    0.38
    relatively
    0.37
    anso
    0.37
    年輕
    0.36
     young
    0.36
    zens
    0.36
    عات
    0.35
    POSITIVE LOGITS
    િવસ
    0.44
     Corpor
    0.40
     საშ
    0.39
     exp
    0.39
    の内
    0.39
     FEATURE
    0.38
    ڱ
    0.38
     incub
    0.37
     constructors
    0.37
     %+
    0.37
    Activations Density 0.031%

    No Known Activations