© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129846
    Prev
    Next
    INDEX
    Explanations

    was ... mö

    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_1_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
    在
    1.20
    도
    1.19
     in
    1.02
     it
    1.02
    ower
    1.02
    こちら
    1.02
    この
    1.00
    shore
    0.95
    広
    0.94
    진
    0.93
    POSITIVE LOGITS
    ва
    1.24
    يي
    1.10
    us
    1.08
    <0x80>
    1.07
    ни
    1.07
    0
    1.02
    يلي
    1.01
    ون
    1.00
     менедже
    0.99
    á
    0.99
    Activations Density 0.001%

    No Known Activations