© 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. 131879
    Prev
    Next
    INDEX
    Explanations

    robusta / bust

    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
    is
    1.84
    c
    1.48
    il
    1.37
    an
    1.26
    ad
    1.23
     on
    1.20
     be
    1.16
    m
    1.16
     for
    1.10
    as
    1.05
    POSITIVE LOGITS
    在
    1.60
     في
    1.45
    </h3>
    1.37
    <0x0D>
    1.20
    も
    1.16
    </b>
    1.14
     в
    1.14
    يري
    1.08
    </i>
    1.07
    </h2>
    1.02
    Activations Density 0.000%

    No Known Activations