© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216380
    Prev
    Next
    INDEX
    Explanations

    specific items or ingredients

    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_47_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
     tangent
    0.49
    Tangent
    0.47
     hatch
    0.43
    berger
    0.42
     ego
    0.40
    нди
    0.39
     R
    0.38
     Gull
    0.38
     tangente
    0.38
     neg
    0.37
    POSITIVE LOGITS
    폴
    0.45
    bim
    0.44
    ალაქ
    0.40
    automatic
    0.39
    }"/>
    0.39
     bial
    0.38
     Sa
    0.38
     Bim
    0.38
     빌
    0.37
     ماشین
    0.36
    Activations Density 0.022%

    No Known Activations