© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196075
    Prev
    Next
    INDEX
    Explanations

    project or incident type

    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_27_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
    Must
    0.42
     perfecto
    0.35
     genitalia
    0.35
     regione
    0.34
    벳
    0.34
    myl
    0.34
    </h3>
    0.33
    bil
    0.33
    彪
    0.33
    MI
    0.33
    POSITIVE LOGITS
    𝘀
    0.36
     תח
    0.35
    áme
    0.35
    分散
    0.35
    രെ
    0.34
    宿舍
    0.34
     Vehicle
    0.34
     shippers
    0.33
    carriers
    0.33
    拡散方程式
    0.33
    Activations Density 0.076%

    No Known Activations