© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216287
    Prev
    Next
    INDEX
    Explanations

    corn

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     triplets
    0.42
     እየሱስ
    0.40
     chmod
    0.38
    بیه
    0.38
    ٽ
    0.37
     triplet
    0.37
     fêtes
    0.37
    ählten
    0.37
    Triplet
    0.37
    ниях
    0.37
    POSITIVE LOGITS
     Lana
    0.43
     Cev
    0.43
     antis
    0.41
     це
    0.40
    鮫
    0.40
    epe
    0.39
     antisemit
    0.39
     Lank
    0.39
    riva
    0.39
    cule
    0.38
    Activations Density 0.000%

    No Known Activations