© 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. 36533
    Prev
    Next
    INDEX
    Explanations

    Roh / RH

    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
    alena
    0.50
    alin
    0.46
    Q
    0.43
    ana
    0.40
    Bx
    0.39
    hof
    0.38
    inti
    0.38
    ina
    0.38
    BD
    0.38
    Caf
    0.38
    POSITIVE LOGITS
    ཊ
    0.42
    obiles
    0.40
    InputDir
    0.40
    ূর্ব
    0.39
     ඔබට
    0.38
    Rut
    0.38
    odimensional
    0.38
    푅
    0.38
     chon
    0.38
    üglich
    0.37
    Activations Density 0.000%

    No Known Activations