© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177373
    Prev
    Next
    INDEX
    Explanations

    device, doc, camera, window, ax

    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_24_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
    Tank
    0.37
     هنا
    0.36
    ază
    0.36
    <unused96>
    0.35
    조
    0.35
     حضور
    0.35
     ←
    0.33
     કિ
    0.33
     HE
    0.32
     aquí
    0.32
    POSITIVE LOGITS
     defamatory
    0.45
    uyi
    0.37
     campaigner
    0.36
    ករណ៍
    0.36
    inescent
    0.35
    erful
    0.35
     sequencer
    0.35
    实现的
    0.34
     erfüll
    0.34
    ponym
    0.34
    Activations Density 0.000%

    No Known Activations