© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86002
    Prev
    Next
    INDEX
    Explanations

    humanity and its relationships

    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_23_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
     लड्डू
    0.42
    сит
    0.38
    接受
    0.37
    Flipper
    0.36
    ել
    0.35
    黢
    0.35
     accept
    0.35
    انیہ
    0.34
    
    0.34
     பச்சை
    0.34
    POSITIVE LOGITS
     truly
    0.39
     gaze
    0.38
     astray
    0.37
    㶲
    0.37
     показ
    0.36
     Schroeder
    0.36
    ammatory
    0.35
     Truly
    0.35
    izion
    0.34
     आवाज
    0.34
    Activations Density 0.009%

    No Known Activations