© 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. 28057
    Prev
    Next
    INDEX
    Explanations

    investigation, FBI, crime scene

    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
    ☦
    0.42
    蛭
    0.41
    会長
    0.38
    ését
    0.38
    राट
    0.38
    チェック
    0.37
     Patriots
    0.37
    estr
    0.36
     sympy
    0.36
    鄱
    0.36
    POSITIVE LOGITS
     Investigation
    1.08
     investigators
    1.05
     investigative
    1.05
     investigation
    1.03
     investigations
    1.01
    Investigation
    1.00
     Investigations
    1.00
     Investigators
    0.98
     investig
    0.93
    Investigations
    0.93
    Activations Density 0.079%

    No Known Activations