© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57966
    Prev
    Next
    INDEX
    Explanations

    human

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     police
    0.44
     vote
    0.41
    }\\
    0.41
     -.
    0.41
    권을
    0.41
     diritti
    0.40
     પોલીસ
    0.40
     quyền
    0.40
    권
    0.40
     Police
    0.39
    POSITIVE LOGITS
     human
    0.86
    human
    0.85
    Human
    0.78
     Human
    0.64
    人間の
    0.64
    人間
    0.61
     HUMAN
    0.61
     челове
    0.57
     मानव
    0.56
     인간
    0.56
    Activations Density 0.004%

    No Known Activations