© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136570
    Prev
    Next
    INDEX
    Explanations

    tasked with

    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_37_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
    <unused17>
    0.37
     Aim
    0.37
    ವು
    0.33
    KeyState
    0.33
     έναν
    0.33
    熬
    0.32
     aim
    0.32
     Autón
    0.32
     ν
    0.32
    拗
    0.32
    POSITIVE LOGITS
     with
    1.06
    with
    1.05
     avec
    1.04
     עם
    0.98
     dengan
    0.96
     với
    0.95
     със
    0.86
    กับการ
    0.85
    With
    0.85
    กับ
    0.82
    Activations Density 0.004%

    No Known Activations