© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131754
    Prev
    Next
    INDEX
    Explanations

    Hunter pond

    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_50_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
     Joe
    0.46
    𝕞
    0.42
     joe
    0.40
    綴
    0.39
    栦
    0.39
     Kelsey
    0.38
     Tomlin
    0.37
     সি
    0.36
    জগতের
    0.36
    Joe
    0.36
    POSITIVE LOGITS
    ダン
    0.40
    Hunter
    0.40
    cas
    0.40
     pond
    0.38
     hunter
    0.38
    Preference
    0.38
    पणे
    0.37
    Blueprint
    0.37
    pond
    0.37
    헌
    0.37
    Activations Density 0.011%

    No Known Activations