© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88693
    Prev
    Next
    INDEX
    Explanations

    aria-label="Open Menu"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    an
    1.08
    R
    0.86
    it
    0.85
    D
    0.77
    ho
    0.76
    about
    0.74
    P
    0.73
    and
    0.73
    S
    0.73
    il
    0.72
    POSITIVE LOGITS
    ות
    0.89
     is
    0.82
     conseguir
    0.71
    ます
    0.68
    тка
    0.65
     expands
    0.64
    দ্বীপ
    0.64
    نی
    0.63
    is
    0.62
     obtains
    0.61
    Activations Density 0.001%

    No Known Activations