© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175528
    Prev
    Next
    INDEX
    Explanations

    guaranteed to impress/drive

    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_24_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
     jeweils
    0.38
     दशा
    0.38
    執
    0.37
     dtype
    0.37
     Mc
    0.37
    เลข
    0.37
     plead
    0.36
     TestAvg
    0.36
     Балтбет
    0.36
     करवा
    0.36
    POSITIVE LOGITS
    venir
    0.41
    <unused41>
    0.38
     CTC
    0.37
    的产品
    0.37
    োলার
    0.37
     কবির
    0.36
     exploratory
    0.36
     ESA
    0.36
     théorie
    0.36
    사는
    0.36
    Activations Density 0.000%

    No Known Activations