© 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. 110295
    Prev
    Next
    INDEX
    Explanations

    posit|posición|posição|positive|позитив

    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
    ع
    1.27
    م
    1.20
     be
    1.16
    ão
    1.14
    ේ
    1.14
    és
    1.05
    ęcie
    1.03
     not
    1.00
     do
    1.00
    un
    0.98
    POSITIVE LOGITS
    i
    1.25
    ।
    1.22
    u
    1.18
    ?
    1.15
    ри
    1.13
    리
    1.13
    。
    1.09
    al
    1.09
     ImageView
    1.06
    1.05
    Activations Density 0.001%

    No Known Activations