© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233425
    Prev
    Next
    INDEX
    Explanations

    stores

    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
    تاج
    0.39
    结论
    0.37
    }]$,
    0.37
    }^{*}$,
    0.37
    🧞
    0.37
     Science
    0.36
     zitten
    0.35
     devolution
    0.35
    嶺
    0.35
     جمع
    0.35
    POSITIVE LOGITS
    材质
    0.40
     MATERIAL
    0.40
    material
    0.39
    Bee
    0.39
     materiali
    0.39
    wdriver
    0.38
    бели
    0.37
    awy
    0.37
    梏
    0.37
    asem
    0.37
    Activations Density 0.000%

    No Known Activations