© 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. 1726
    Prev
    Next
    INDEX
    Explanations

    home advantage

    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
     diverted
    0.39
     screaming
    0.38
     diverting
    0.37
     Nationalist
    0.36
    ൺ
    0.35
    哭
    0.35
    钱
    0.35
     সম্রাট
    0.35
    鯢
    0.35
     निगम
    0.34
    POSITIVE LOGITS
     hom
    0.42
     Home
    0.39
     home
    0.38
    Home
    0.37
    Hom
    0.36
     Hom
    0.36
     Sussex
    0.35
    Checkout
    0.35
    hom
    0.35
     Brandon
    0.34
    Activations Density 0.008%

    No Known Activations