© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131891
    Prev
    Next
    INDEX
    Explanations

    два (two) or две (two)

    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_1_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
    t
    1.48
    the
    1.34
    s
    1.25
    kr
    1.08
    k
    1.05
    (
    1.04
    [
    1.04
    y
    1.03
    ی
    1.03
    ال
    1.02
    POSITIVE LOGITS
    л
    1.37
     a
    1.24
     paix
    1.12
     marav
    1.11
     propriedades
    1.09
     plataformas
    1.07
     тех
    1.04
     minhas
    1.03
     dizer
    1.02
     faça
    1.02
    Activations Density 0.000%

    No Known Activations