© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2486
    Prev
    Next
    INDEX
    Explanations

    `.gitignore` and `docker` exclusion files

    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_39_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
     flog
    0.43
     coffin
    0.41
    निम्
    0.38
    撵
    0.38
    Ship
    0.38
     подска
    0.38
     dor
    0.37
     aDict
    0.37
    <unused48>
    0.37
     liht
    0.37
    POSITIVE LOGITS
    Ab
    0.38
    ᵉ
    0.38
     اقتص
    0.37
    𝙈
    0.37
     जोड़
    0.36
    mik
    0.36
     கொண்டிருந்த
    0.36
     দেওয়া
    0.36
     Configuration
    0.35
     বলা
    0.35
    Activations Density 0.000%

    No Known Activations