© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134335
    Prev
    Next
    INDEX
    Explanations

    aerospike, buckthorn, Hampstead, Chad

    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_6_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
    י
    1.09
    i
    1.01
     recombination
    0.94
     cystic
    0.91
     to
    0.91
     synapse
    0.88
     styrene
    0.87
    ]
    0.86
     mucus
    0.86
     marinade
    0.86
    POSITIVE LOGITS
    ag
    1.15
    imizi
    1.00
     Реа
    0.91
    ik
    0.91
    aw
    0.91
     Неза
    0.91
    iz
    0.87
    ott
    0.87
    ifting
    0.86
    ov
    0.86
    Activations Density 0.000%

    No Known Activations