© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79617
    Prev
    Next
    INDEX
    Explanations

    leading followed by nouns

    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_0_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
     swoich
    1.25
    يت
    1.18
    </h3>
    1.17
     I
    1.16
     afiliados
    1.16
    Ε
    1.13
    С
    1.12
     Achilles
    1.09
     SOR
    1.09
     dobry
    1.09
    POSITIVE LOGITS
    س
    1.60
    res
    1.55
    os
    1.52
    ic
    1.41
    ä
    1.41
    с
    1.36
    ie
    1.34
    د
    1.34
    ス
    1.34
    ens
    1.32
    Activations Density 0.009%

    No Known Activations