© 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. 107803
    Prev
    Next
    INDEX
    Explanations

    asciidoctor, asp, appli, els, giv

    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
     as
    1.94
     are
    1.50
     you
    1.28
    als
    1.27
    س
    1.24
    ला
    1.17
    ier
    1.15
     have
    1.12
    den
    1.10
    se
    1.08
    POSITIVE LOGITS
    ي
    1.45
    ৫
    1.38
    י
    1.35
    ر
    1.34
    ميل
    1.16
    이라
    1.15
    ه
    1.15
    ويل
    1.11
    يرا
    1.09
    ৪
    1.08
    Activations Density 0.000%

    No Known Activations