© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236776
    Prev
    Next
    INDEX
    Explanations

    Dear

    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
    গ্ধ
    0.39
     Spor
    0.39
     दु
    0.37
    哽
    0.37
    }]}
    0.37
    обу
    0.36
     subjects
    0.36
     shells
    0.35
     footh
    0.34
     Senior
    0.34
    POSITIVE LOGITS
     terminus
    0.39
    endas
    0.39
    studies
    0.38
    Cô
    0.37
    ờ
    0.36
    study
    0.36
    compre
    0.36
    മാര്‍
    0.35
     مورد
    0.35
    Sha
    0.34
    Activations Density 0.000%

    No Known Activations