© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    mixed economy academic syllabus graduate programme assessment

    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
    orbit
    0.47
    monitoring
    0.44
    PACK
    0.44
    orbital
    0.44
     monitoring
    0.42
     pulmonary
    0.41
    범
    0.41
     orbit
    0.41
    equal
    0.40
     Pulmonary
    0.40
    POSITIVE LOGITS
     provision
    0.55
    Provision
    0.53
     Provision
    0.48
    provision
    0.46
     бк
    0.36
    щим
    0.36
    Tou
    0.36
     unre
    0.35
     хвата
    0.35
     ㅛ
    0.35
    Activations Density 0.022%

    No Known Activations