© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135578
    Prev
    Next
    INDEX
    Explanations

    nginx server configuration

    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_37_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
    ഫ
    0.42
    survey
    0.40
    Julie
    0.39
     թ
    0.37
     intervene
    0.37
    ISTS
    0.36
    respond
    0.36
    secure
    0.36
    配置
    0.36
     secur
    0.36
    POSITIVE LOGITS
    र्च
    0.38
     Muc
    0.38
    🧼
    0.38
     Lucky
    0.38
     गन्ना
    0.38
     adsorbent
    0.38
    하시는
    0.38
     rustic
    0.37
     হবি
    0.37
     Probe
    0.36
    Activations Density 0.001%

    No Known Activations