© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15479
    Prev
    Next
    INDEX
    Explanations

    generating image parameters like --ar

    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
     تف
    0.39
     ComVisible
    0.39
     Profiles
    0.38
    ocyanate
    0.37
     pary
    0.36
    十八章
    0.36
    誦
    0.36
     pram
    0.35
     elb
    0.35
    getText
    0.35
    POSITIVE LOGITS
    ificantly
    0.38
    Damage
    0.38
     مقارنه
    0.37
    Kunst
    0.37
    Debug
    0.37
    Dependency
    0.37
     Reconciliation
    0.37
    Painting
    0.36
    ))$
    0.36
     Kupfer
    0.36
    Activations Density 0.090%

    No Known Activations