© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89423
    Prev
    Next
    INDEX
    Explanations

    traditional food source

    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_23_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
    憸
    0.44
     ].
    0.42
     morales
    0.42
     greed
    0.40
     nub
    0.39
     снова
    0.39
     динами
    0.39
     dynamically
    0.39
    ybės
    0.38
    ｜
    0.38
    POSITIVE LOGITS
     understands
    0.44
    typing
    0.41
    collation
    0.39
     knew
    0.38
    carrying
    0.38
     carrying
    0.37
     understood
    0.37
    trusted
    0.36
    understood
    0.36
    understand
    0.36
    Activations Density 0.055%

    No Known Activations