© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36535
    Prev
    Next
    INDEX
    Explanations

    thyroid issues

    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_31_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
    wendung
    0.38
     locatie
    0.37
    瘘
    0.37
    stepping
    0.37
    当作
    0.37
     "'";
    0.36
    reached
    0.36
     Inbetriebnahme
    0.35
    会場
    0.35
     médec
    0.34
    POSITIVE LOGITS
     penetrate
    0.44
     myfile
    0.40
     mision
    0.40
     audited
    0.39
    濛
    0.39
    सो
    0.38
    ipients
    0.38
    égio
    0.37
     códigos
    0.36
     dbcontext
    0.36
    Activations Density 0.057%

    No Known Activations