© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    directory, file, or string existence checks

    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
    蟲
    0.36
    審査
    0.36
     ipotesi
    0.36
     dirs
    0.35
     NIA
    0.35
    Як
    0.34
    技能
    0.34
    Arch
    0.34
     délégation
    0.33
    ▬▬▬▬
    0.32
    POSITIVE LOGITS
    explicit
    0.42
     illuminating
    0.40
     explicit
    0.40
     illuminates
    0.39
     illuminate
    0.37
    ደጋ
    0.36
     explicitly
    0.36
     illuminated
    0.36
     Explicit
    0.36
     illumin
    0.35
    Activations Density 0.013%

    No Known Activations