© 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. 132265
    Prev
    Next
    INDEX
    Explanations

    hinter, posterior

    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
    s
    1.27
    has
    1.26
    x
    1.21
    t
    1.20
    2
    1.19
    ما
    1.16
    c
    1.15
    is
    1.09
    m
    1.05
    نا
    1.03
    POSITIVE LOGITS
    з
    1.23
    зів
    1.09
     are
    1.07
    ),
    1.03
    quela
    1.03
     genetically
    1.02
     wurde
    1.02
     können
    1.02
     machen
    1.02
     wäre
    1.00
    Activations Density 0.000%

    No Known Activations