© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116960
    Prev
    Next
    INDEX
    Explanations

    order total amount status

    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_38_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
    startY
    0.44
     பாத
    0.43
    $.)
    0.43
    Starting
    0.40
     Fields
    0.40
    isRequired
    0.40
     শুরু
    0.39
    開始
    0.39
    樎
    0.39
     পণ
    0.39
    POSITIVE LOGITS
    ிலை
    0.41
     delivered
    0.40
     SAFETY
    0.40
     moderately
    0.39
     mida
    0.38
     testimonies
    0.37
    ندہ
    0.37
     assertive
    0.37
     XC
    0.36
     completos
    0.35
    Activations Density 0.003%

    No Known Activations