© 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. 203154
    Prev
    Next
    INDEX
    Explanations

    say Mid

    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
    ostrat
    0.40
    嬬
    0.39
     cytology
    0.38
     معه
    0.38
     Lug
    0.38
     Active
    0.38
     routines
    0.37
    ANCY
    0.36
    钣
    0.36
     contexts
    0.36
    POSITIVE LOGITS
    起的
    0.38
    Quarter
    0.38
    Translator
    0.36
    airro
    0.36
    ploader
    0.36
    כת
    0.35
    URF
    0.35
     सिंगल
    0.35
     Burden
    0.35
     Quarterly
    0.34
    Activations Density 0.003%

    No Known Activations