© 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. 215727
    Prev
    Next
    INDEX
    Explanations

    altitude feet

    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
    Foot
    2.05
     Foot
    2.02
     foot
    2.00
    foot
    1.96
     FOOT
    1.88
    FOOT
    1.80
     Fuß
    1.70
    足
    1.64
     voet
    1.62
     feet
    1.58
    POSITIVE LOGITS
    liers
    0.38
    ļ
    0.38
    urrent
    0.36
    螳
    0.35
     نص
    0.34
    wall
    0.33
     Milo
    0.33
     Jiang
    0.33
     Mattress
    0.33
    atic
    0.32
    Activations Density 0.001%

    No Known Activations