© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53264
    Prev
    Next
    INDEX
    Explanations

    description

    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_30_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
    Strategies
    0.42
    ໄວ
    0.40
    McDonald
    0.37
    filt
    0.37
    फड
    0.37
     Strategies
    0.36
    㗎
    0.35
    Interior
    0.35
     страте
    0.35
     strategies
    0.34
    POSITIVE LOGITS
     অথবা
    0.42
     ziua
    0.39
    舒
    0.39
     Shabd
    0.37
     以及
    0.37
     സൂര്യ
    0.37
     overview
    0.36
    一是
    0.36
     Succession
    0.36
     dle
    0.36
    Activations Density 0.015%

    No Known Activations