© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214027
    Prev
    Next
    INDEX
    Explanations

    sinking

    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_47_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
    adeus
    0.45
    Escolhido
    0.40
     Weinberg
    0.40
    fired
    0.39
    cho
    0.38
    Schw
    0.38
    베
    0.38
    ₩
    0.38
    वीन
    0.37
    ኼ
    0.37
    POSITIVE LOGITS
     elevating
    0.43
     permeate
    0.40
     multilevel
    0.39
     inserting
    0.38
     inlets
    0.38
     अभिया
    0.37
    cter
    0.37
     insertar
    0.37
     interstitial
    0.37
     persists
    0.37
    Activations Density 0.002%

    No Known Activations