© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88244
    Prev
    Next
    INDEX
    Explanations

    `action` input

    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_18_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
    give
    0.44
    ：
    0.43
    conductor
    0.43
    if
    0.42
    viii
    0.41
     composés
    0.41
    prove
    0.40
     बने
    0.40
    tell
    0.40
    -:
    0.40
    POSITIVE LOGITS
     Prada
    0.53
    ισε
    0.47
     Paramount
    0.45
     para
    0.44
     Macau
    0.44
     Пара
    0.43
     MGM
    0.43
    ândia
    0.43
     weder
    0.42
     quelle
    0.41
    Activations Density 0.000%

    No Known Activations