© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132098
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_50_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
     rock
    0.46
     ear
    0.44
    ()}\
    0.38
    ths
    0.38
     зали
    0.37
     Rock
    0.36
     рок
    0.36
     écr
    0.36
     chemical
    0.35
     precip
    0.35
    POSITIVE LOGITS
    ｑ
    0.44
    mont
    0.41
     क्‍
    0.40
     Que
    0.38
    वेश
    0.38
     Cress
    0.38
    ју
    0.37
    ಮು
    0.37
    馬
    0.37
     Swords
    0.36
    Activations Density 0.012%

    No Known Activations