© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12133
    Prev
    Next
    INDEX
    Explanations

    body parts and height

    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_40_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
    嬉
    0.38
    ದುಕೊಳ್ಳ
    0.36
    wellery
    0.36
     Nk
    0.36
    kušen
    0.36
    شاء
    0.36
    탬
    0.36
     ინ
    0.35
    мили
    0.35
     deh
    0.35
    POSITIVE LOGITS
     height
    1.13
    Height
    1.09
     Height
    1.06
    height
    1.05
     altura
    0.88
    高さ
    0.85
     высота
    0.84
     hoogte
    0.82
    HEIGHT
    0.81
     HEIGHT
    0.80
    Activations Density 0.040%

    No Known Activations