© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213067
    Prev
    Next
    INDEX
    Explanations

    battery capacity unit

    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_5_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
    <0x98>
    1.14
    <0xA6>
    1.13
    ين
    1.07
    <0xA2>
    1.05
    <0x92>
    1.05
    ни
    1.02
    <0x99>
    1.02
    <0xAC>
    1.00
    もら
    1.00
    ні
    0.98
    POSITIVE LOGITS
    us
    1.24
    ↵↵
    1.23
    ing
    1.18
     for
    1.14
    (
    1.09
    '
    1.05
    te
    1.03
    ant
    1.02
    ט
    1.02
    ä
    1.02
    Activations Density 0.000%

    No Known Activations