© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57826
    Prev
    Next
    INDEX
    Explanations

    Graph

    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_59_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
    RENT
    0.42
    ENCY
    0.40
    舧
    0.38
    டத்தில்
    0.38
    école
    0.37
    transformer
    0.37
     تصاویر
    0.37
    িত্র
    0.36
    TEXTURE
    0.35
    謬
    0.35
    POSITIVE LOGITS
    ki
    0.48
    cool
    0.46
    ship
    0.46
    cap
    0.46
    ol
    0.44
     cool
    0.44
    pap
    0.44
    sco
    0.43
    olo
    0.43
    cr
    0.43
    Activations Density 0.001%

    No Known Activations