© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162902
    Prev
    Next
    INDEX
    Explanations

    ask for help

    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_31_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
     noto
    0.41
     NIL
    0.39
    懶
    0.39
     वस
    0.38
    الق
    0.38
     claire
    0.37
     bords
    0.37
     estação
    0.37
     relief
    0.37
     Niveau
    0.37
    POSITIVE LOGITS
    ])]
    0.38
    umball
    0.36
    ANSAS
    0.36
    決して
    0.35
    monton
    0.35
    юн
    0.34
     bood
    0.34
     OXIDES
    0.34
     mortal
    0.33
    IY
    0.33
    Activations Density 0.004%

    No Known Activations