© 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. 32123
    Prev
    Next
    INDEX
    Explanations

    standards department received

    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
     Devon
    0.41
    ቦ
    0.39
     McConnell
    0.38
    cambrian
    0.38
    चूर
    0.37
    กรรมการ
    0.37
     স্বাস্থ্য
    0.37
     Đức
    0.36
    acce
    0.36
    匕
    0.36
    POSITIVE LOGITS
     prov
    0.52
    Prov
    0.41
     NSF
    0.40
    prov
    0.38
     اج
    0.38
     прово
    0.37
    Liquid
    0.37
     Induction
    0.36
     induction
    0.35
    Patent
    0.35
    Activations Density 0.038%

    No Known Activations