© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 197597
    Prev
    Next
    INDEX
    Explanations

    av

    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
     Δια
    0.37
     తే
    0.37
    constraintStart
    0.36
     vina
    0.36
    맥
    0.36
    ambat
    0.36
    itemBackground
    0.36
     பிச்சு
    0.35
     হেম
    0.35
     IRR
    0.35
    POSITIVE LOGITS
    Cath
    0.43
    𝕘
    0.42
    ючи
    0.42
     Hacienda
    0.41
    MUS
    0.39
    Mt
    0.38
     donner
    0.38
    ayani
    0.38
     গ
    0.37
    Middle
    0.37
    Activations Density 0.000%

    No Known Activations