© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150194
    Prev
    Next
    INDEX
    Explanations

    Debian hardware architectures

    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
    ب
    0.54
    妒
    0.48
    зом
    0.44
     comme
    0.43
    ندس
    0.43
    相
    0.43
    ቅ
    0.42
     догово
    0.41
    ৌর
    0.41
     obscures
    0.41
    POSITIVE LOGITS
    ആര്‍
    0.53
     NAS
    0.47
     Prosecutor
    0.47
     Waiver
    0.47
    atsi
    0.46
     Resources
    0.46
    নাথ
    0.46
     Dokl
    0.46
     Qualifier
    0.45
    ᴀ
    0.45
    Activations Density 0.000%

    No Known Activations