© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33104
    Prev
    Next
    INDEX
    Explanations

    repeat until convergence

    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_31_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
     સર્
    0.38
    ₁(
    0.35
    銳
    0.33
     PACS
    0.32
     ሁለት
    0.32
    емом
    0.32
     மேலும்
    0.31
    <unused65>
    0.31
     CONTINUE
    0.30
    次的
    0.30
    POSITIVE LOGITS
     mayhem
    0.32
     swimwear
    0.31
     entertainment
    0.30
     devastation
    0.30
    ટી
    0.30
    Entertainment
    0.30
    otland
    0.30
    ẋ
    0.30
     Anger
    0.29
    ambar
    0.29
    Activations Density 0.000%

    No Known Activations