© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59514
    Prev
    Next
    INDEX
    Explanations

    combination of words ending in -ation followed by -ary

    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_2_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
    1
    1.35
    า
    1.19
    2
    1.09
    that
    1.05
    to
    1.04
    9
    1.03
     Desar
    1.02
    shard
    1.00
    f
    1.00
    so
    0.99
    POSITIVE LOGITS
    ில்
    1.13
    ت
    1.07
    ó
    1.07
    ed
    1.04
    л
    1.02
     murderer
    1.00
     voltar
    1.00
     fable
    0.99
     trouver
    0.98
     detector
    0.98
    Activations Density 0.000%

    No Known Activations