© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41767
    Prev
    Next
    INDEX
    Explanations

    code execution and inspection

    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_22_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
    ޑ
    0.37
     either
    0.36
     பதில
    0.35
    डिया
    0.34
    糈
    0.34
    保安
    0.32
     resp
    0.32
     चुनौती
    0.32
     निर्देशक
    0.32
     coûte
    0.32
    POSITIVE LOGITS
    カ
    0.42
    Purpose
    0.39
    ヒ
    0.39
    би
    0.38
    Deterministic
    0.38
    운
    0.38
    Genes
    0.35
    イ
    0.35
    roots
    0.34
    Beschreibung
    0.34
    Activations Density 0.000%

    No Known Activations