© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17551
    Prev
    Next
    INDEX
    Explanations

    vibe check on each

    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_15_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
     spectrometers
    0.41
     👀
    0.39
     spectroscopy
    0.38
     :");
    0.37
     favorably
    0.37
     spectroscopic
    0.36
     spectators
    0.35
     ót
    0.35
     intently
    0.35
     optimizes
    0.35
    POSITIVE LOGITS
    al
    0.39
    ；
    0.39
    ؛
    0.39
    at
    0.38
    lla
    0.37
    anch
    0.37
    ly
    0.37
    usp
    0.37
    use
    0.36
    than
    0.36
    Activations Density 0.026%

    No Known Activations