© 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. 167091
    Prev
    Next
    INDEX
    Explanations

    mental health and child treatment

    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
     deaf
    0.42
    LightTheme
    0.38
    ద్ధ
    0.38
     antibodies
    0.38
    deload
    0.38
    ourced
    0.37
    Ṕ
    0.37
    ᚗ
    0.37
    Slim
    0.36
    Purg
    0.36
    POSITIVE LOGITS
     BB
    0.41
     Corbett
    0.38
    स्थिति
    0.38
     balcony
    0.37
    {!
    0.37
     Psic
    0.36
     temper
    0.36
     Bb
    0.36
     সম্পত্তির
    0.36
    景观
    0.35
    Activations Density 0.022%

    No Known Activations