© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9807
    Prev
    Next
    INDEX
    Explanations

    want to

    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_40_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
     Gründen
    0.42
     tatsächlich
    0.41
     actually
    0.41
     संध्या
    0.40
    ".*:
    0.39
     Dempsey
    0.37
     сан
    0.36
     ছাউ
    0.36
    雳
    0.36
     auricular
    0.35
    POSITIVE LOGITS
    ijo
    0.39
    Bened
    0.38
    udes
    0.38
     ensure
    0.37
     sør
    0.37
    ije
    0.37
    enez
    0.36
     ANG
    0.36
    nje
    0.35
    BackPressed
    0.34
    Activations Density 0.041%

    No Known Activations