© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58201
    Prev
    Next
    INDEX
    Explanations

    lucrative opportunities

    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_11_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
    "},
    0.62
    </sub>
    0.61
    arrivals
    0.61
    ."},
    0.59
    cluding
    0.58
    '},
    0.58
    ixas
    0.57
     когда
    0.57
    ن
    0.55
     άνθρω
    0.55
    POSITIVE LOGITS
    ः
    0.64
    ंक्शन
    0.53
     voiture
    0.52
    葬
    0.52
    зи
    0.52
    서
    0.52
    ებთ
    0.51
     Moyen
    0.50
    c
    0.50
    ας
    0.50
    Activations Density 0.001%

    No Known Activations