© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37836
    Prev
    Next
    INDEX
    Explanations

    leans back

    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_11_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
    󰡔
    0.52
    ຂອງ
    0.52
     departments
    0.51
    endidikan
    0.50
    ).”
    0.48
    Departments
    0.48
    यिक
    0.48
     mosques
    0.48
     Screening
    0.47
    ரூராட்சி
    0.47
    POSITIVE LOGITS
    r
    0.63
    ší
    0.53
     coupler
    0.52
    سي
    0.49
    وسي
    0.48
     ولك
    0.48
    }$.
    0.46
     igen
    0.46
    și
    0.46
     أبريل
    0.46
    Activations Density 0.000%

    No Known Activations