© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143371
    Prev
    Next
    INDEX
    Explanations

    fuel prices

    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_46_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
     pied
    0.41
    élect
    0.39
     allons
    0.39
    ताई
    0.38
     océ
    0.38
     titular
    0.38
    সৌ
    0.38
    砼
    0.37
     tay
    0.37
     eenvoud
    0.37
    POSITIVE LOGITS
    idh
    0.44
     accumulation
    0.42
    Dep
    0.37
    まと
    0.37
     kup
    0.37
     Depot
    0.36
    듣
    0.36
    रेज
    0.36
     depots
    0.36
     ситуация
    0.36
    Activations Density 0.000%

    No Known Activations