© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150438
    Prev
    Next
    INDEX
    Explanations

    PCBs, dioxins, phthalates

    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_18_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
     convain
    0.47
     adenosine
    0.46
    MJ
    0.43
     কলা
    0.43
     sağ
    0.43
     μέρος
    0.43
    }\
    0.43
     méthod
    0.42
    只不过
    0.42
     dextrose
    0.42
    POSITIVE LOGITS
    gateway
    0.43
     renegoti
    0.42
    განი
    0.42
    きの
    0.41
    얽
    0.41
    狭
    0.40
    openid
    0.40
    ási
    0.40
    マルチ
    0.40
    rat
    0.39
    Activations Density 0.000%

    No Known Activations