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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157577
    Prev
    Next
    INDEX
    Explanations

    VA (Virginia), VA (fintech app), VA (Volt-Amperes), VA (Vertical Alignment)

    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
    1.50
    n
    1.24
    il
    1.20
    i
    1.14
    ن
    1.14
    ない
    1.10
    ות
    1.07
    A
    1.05
    н
    1.05
    us
    1.03
    POSITIVE LOGITS
    ك
    1.21
    ية
    1.00
    \
    0.99
     as
    0.98
    的
    0.98
    एस
    0.96
     ૨
    0.93
    0.92
    ные
    0.87
    мо
    0.87
    Activations Density 0.000%

    No Known Activations