© 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. 215949
    Prev
    Next
    INDEX
    Explanations

    rent/hire

    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
    imani
    0.41
    ெ
    0.39
     Sandy
    0.38
    imai
    0.38
    irai
    0.38
     পর্বত
    0.38
    stash
    0.38
    lys
    0.37
    iliary
    0.37
    erosene
    0.37
    POSITIVE LOGITS
    üedad
    0.40
     ത
    0.39
     pang
    0.37
    忿
    0.36
    이드
    0.35
     Führ
    0.35
     đưa
    0.35
    hadoop
    0.35
    ాడు
    0.34
     EST
    0.34
    Activations Density 0.002%

    No Known Activations