© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32281
    Prev
    Next
    INDEX
    Explanations

    highly recommend

    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_31_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
    是非
    0.40
    ぜひ
    0.38
     желательно
    0.37
    심히
    0.36
    वीस
    0.35
     proud
    0.34
     regroup
    0.32
    滅
    0.32
    చ్చి
    0.31
     होईल
    0.30
    POSITIVE LOGITS
    Board
    0.34
    arding
    0.33
    Regarding
    0.32
    bares
    0.32
    puts
    0.31
    regarding
    0.31
    Getting
    0.30
    PSE
    0.30
     حنا
    0.30
     गारंटी
    0.30
    Activations Density 0.002%

    No Known Activations