© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178085
    Prev
    Next
    INDEX
    Explanations

    vir

    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
    yendo
    0.39
     graduating
    0.38
    "`
    0.38
     ag
    0.38
    ayam
    0.38
    hofer
    0.38
     descent
    0.36
     cay
    0.36
    ാരം
    0.36
    garten
    0.36
    POSITIVE LOGITS
     ParkingLot
    0.42
    ـــ
    0.41
    unile
    0.41
    𝒅
    0.40
    乱流
    0.40
     प्रवीण
    0.40
     колеба
    0.39
    रोक
    0.39
    epine
    0.39
     Vail
    0.38
    Activations Density 0.000%

    No Known Activations