© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260847
    Prev
    Next
    INDEX
    Explanations

    importance and prioritization

    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
     செய்தி
    0.43
     razão
    0.41
    rente
    0.38
    mouse
    0.38
    нета
    0.38
     главным
    0.38
    ☬
    0.38
     keyboards
    0.37
    🗣
    0.37
     ய
    0.37
    POSITIVE LOGITS
    udence
    0.47
     innermost
    0.46
     PROCUREMENT
    0.45
     opposing
    0.40
     wondering
    0.40
     unwavering
    0.39
     undulating
    0.39
    默默
    0.38
    पो
    0.38
     utmost
    0.38
    Activations Density 0.000%

    No Known Activations