© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109799
    Prev
    Next
    INDEX
    Explanations

    Ibiza, Ibérica, Ibovespa

    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_2_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
     is
    1.30
    ai
    1.19
     be
    1.11
     it
    1.06
     profissionais
    0.99
     to
    0.98
    ies
    0.98
    は
    0.97
    یت
    0.96
     are
    0.95
    POSITIVE LOGITS
    t
    1.83
    <0x80>
    1.55
    m
    1.15
    k
    1.12
    r
    1.11
    b
    1.11
    1
    1.09
    st
    1.07
    f
    1.05
    src
    1.02
    Activations Density 0.000%

    No Known Activations