© 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. 245173
    Prev
    Next
    INDEX
    Explanations

    blood infections and medical school

    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
     tratando
    0.40
     Schaden
    0.38
    вища
    0.38
     })_{
    0.37
     उपयोगकर्ता
    0.37
    ResponseEntity
    0.37
     ROY
    0.37
     electroph
    0.36
    ندس
    0.36
     conformity
    0.35
    POSITIVE LOGITS
    PI
    0.42
    workItem
    0.39
    ]-->
    0.38
    sing
    0.37
    aband
    0.37
    hall
    0.36
     mainstream
    0.36
    粗
    0.36
    barung
    0.36
    Tracker
    0.35
    Activations Density 0.000%

    No Known Activations