© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196473
    Prev
    Next
    INDEX
    Explanations

    model builder

    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_4_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
     is
    1.32
    to
    1.02
    ﺭ
    1.00
    on
    0.95
    times
    0.88
    να
    0.88
    inning
    0.88
    metros
    0.87
    is
    0.87
    pay
    0.84
    POSITIVE LOGITS
     Modelling
    1.02
    ;
    1.01
     Modell
    0.89
    ة
    0.88
    }
    0.88
     Modeling
    0.86
     Modelle
    0.86
    ض
    0.86
    ט
    0.86
    รอบ
    0.84
    Activations Density 0.004%

    No Known Activations