© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12806
    Prev
    Next
    INDEX
    Explanations

    match and group

    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_40_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
     வண்ணப்பூச்சு
    0.16
     აღმასრულ
    0.16
    poder
    0.15
    ക്ക്‌
    0.15
     வண்ணப்பூ
    0.14
     MyDB
    0.14
    Ⅺ
    0.14
     എന്ന്
    0.14
    manirrahim
    0.14
     kaisi
    0.14
    POSITIVE LOGITS
     stratum
    0.15
     individual
    0.13
     "
    0.12
     Retrieved
    0.12
     inter
    0.12
    ]
    0.12
     retrieved
    0.12
     ion
    0.12
    heter
    0.12
     sis
    0.12
    Activations Density 0.203%

    No Known Activations