© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68453
    Prev
    Next
    INDEX
    Explanations

    Console

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Network
    0.44
    Claim
    0.43
    Review
    0.42
    System
    0.42
    Files
    0.40
    Customer
    0.40
    바
    0.39
     görmek
    0.39
    ordering
    0.39
    Compat
    0.39
    POSITIVE LOGITS
     liberty
    0.44
    vection
    0.43
    
    0.41
     correlates
    0.40
     جانب
    0.40
    ᔨ
    0.39
     correlating
    0.39
     pry
    0.39
    ﾒ
    0.38
    ulsion
    0.38
    Activations Density 0.001%

    No Known Activations