© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61980
    Prev
    Next
    INDEX
    Explanations

    tinkling sounds or suffixes

    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
    亻
    0.54
     escuch
    0.49
     Luzon
    0.49
    rvGroup
    0.49
    }_{
    0.47
    }$).
    0.47
     Oké
    0.47
    อายุ
    0.47
     亻
    0.47
     berd
    0.47
    POSITIVE LOGITS
     specialises
    0.57
     derives
    0.51
     contains
    0.50
     emphasises
    0.50
     endeavors
    0.49
     emphasizes
    0.49
     focuses
    0.48
     incorporates
    0.48
     specializes
    0.47
     demonstrates
    0.47
    Activations Density 0.000%

    No Known Activations