© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28288
    Prev
    Next
    INDEX
    Explanations

    RTX 0, trench coat, container ship, vapor., office action, sales orders, mesh size, filler list

    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_40_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
    burne
    0.34
    rVert
    0.34
     ВО
    0.34
     gulp
    0.33
    artifacts
    0.33
    egu
    0.33
    グ
    0.33
     그
    0.33
     artifact
    0.32
     heure
    0.32
    POSITIVE LOGITS
    न्यूयॉर्क
    0.40
     мүмкүн
    0.40
    မြင့်
    0.40
    纨
    0.38
    loir
    0.38
     شاه
    0.38
    $>$
    0.38
     Altogether
    0.37
    $>
    0.37
     mencoba
    0.37
    Activations Density 0.758%

    No Known Activations