© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149312
    Prev
    Next
    INDEX
    Explanations

    about or means

    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_23_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
     converg
    0.41
     lepid
    0.38
    𝘦
    0.38
     corrid
    0.38
     deser
    0.38
     comidas
    0.37
     temps
    0.37
     diap
    0.37
     uart
    0.36
     unite
    0.36
    POSITIVE LOGITS
     erkennen
    0.40
    সকল
    0.39
     टू
    0.39
     অ্যান্ড
    0.39
     Planned
    0.38
    <i>
    0.38
     Reality
    0.37
    fontawesome
    0.36
    问道
    0.36
     утра
    0.36
    Activations Density 0.011%

    No Known Activations