© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219318
    Prev
    Next
    INDEX
    Explanations

    scientific publishers and journals

    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_31_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
    র্দ
    0.36
    ShowWindow
    0.36
     কৃষ
    0.36
    <&
    0.36
    ^{+}$.
    0.36
     hypersur
    0.34
    ClearedBy
    0.34
     AGRICULTURE
    0.34
    ^{*}=
    0.34
    ethoscope
    0.33
    POSITIVE LOGITS
     resident
    0.37
    ̀
    0.35
    əri
    0.35
    Resident
    0.34
     P
    0.34
     parece
    0.33
     plateau
    0.33
     ليها
    0.33
     Resident
    0.33
     metallic
    0.33
    Activations Density 0.001%

    No Known Activations