© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2369
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones

    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_44_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
     ماهی
    0.40
    HANDLE
    0.38
    Dragon
    0.37
     expired
    0.37
    
    0.36
    findOrFail
    0.36
    کنندگان
    0.36
     impegno
    0.36
    |>
    0.36
     სახელმწიფ
    0.36
    POSITIVE LOGITS
    Ст
    0.44
     UT
    0.44
    claim
    0.42
    BlackElo
    0.40
     අන
    0.39
     CLL
    0.39
     claim
    0.38
    };
    0.38
     PRC
    0.37
     Arqu
    0.37
    Activations Density 0.005%

    No Known Activations