© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199588
    Prev
    Next
    INDEX
    Explanations

    R code documentation

    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
    ISTICS
    0.40
    굉
    0.39
    jskim
    0.39
    ｸ
    0.38
    ーリー
    0.38
    ora
    0.37
     traff
    0.37
    elace
    0.36
    ashvili
    0.36
    heiros
    0.35
    POSITIVE LOGITS
    韋
    0.50
    韦
    0.44
    Network
    0.40
    ఫ
    0.38
     tubules
    0.38
     hostage
    0.36
     uve
    0.36
    uve
    0.35
     Holly
    0.35
    новен
    0.35
    Activations Density 0.000%

    No Known Activations