© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196574
    Prev
    Next
    INDEX
    Explanations

    reproducibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     na
    0.60
     d
    0.55
     du
    0.53
    力
    0.52
     mar
    0.51
    voja
    0.50
     jeden
    0.49
     tiên
    0.49
     jedna
    0.48
     me
    0.48
    POSITIVE LOGITS
    ಐ
    0.52
    蕲
    0.51
    식을
    0.50
    itemId
    0.50
    Schn
    0.50
     سوریه
    0.48
     পাগ
    0.47
    Objective
    0.47
    Fancy
    0.47
    拡散
    0.46
    Activations Density 0.002%

    No Known Activations