© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17342
    Prev
    Next
    INDEX
    Explanations

    useless

    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
    서트
    0.41
    봇
    0.36
     Updating
    0.35
     ထ
    0.35
    塑料
    0.35
    ন্ত
    0.34
    oplastic
    0.34
    𝘆
    0.34
     Bot
    0.34
     firm
    0.33
    POSITIVE LOGITS
     ঈশ্বরের
    0.44
     doing
    0.44
    epis
    0.41
     goodness
    0.41
    Doing
    0.40
     Doing
    0.40
     Czechoslovak
    0.39
     আশীর
    0.39
     do
    0.39
     cricketers
    0.39
    Activations Density 0.022%

    No Known Activations