© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116247
    Prev
    Next
    INDEX
    Explanations

    **Feature / Scenario blocks in Gherkin**

    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
    istock
    0.44
    invited
    0.42
    addon
    0.40
    創
    0.40
    creation
    0.40
    luoro
    0.40
    ALG
    0.39
    Aplic
    0.38
    iley
    0.38
    creat
    0.38
    POSITIVE LOGITS
     словами
    0.34
    ("#
    0.34
     баш
    0.33
    ,",
    0.33
     Determination
    0.33
     תש
    0.33
     slug
    0.33
    ]["
    0.32
    ने
    0.31
     प्रतिबंध
    0.31
    Activations Density 0.000%

    No Known Activations