© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51264
    Prev
    Next
    INDEX
    Explanations

    contar, producing, risk, investing, selling

    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
     egregious
    0.41
     exclusionary
    0.39
     dissociation
    0.38
     inoculation
    0.38
     whereby
    0.37
     abstinence
    0.37
     nghề
    0.37
    梱
    0.37
     excitatory
    0.36
     depolarization
    0.36
    POSITIVE LOGITS
     executing
    0.48
    Bitmap
    0.47
     mengeluarkan
    0.46
    Pil
    0.45
     keeping
    0.44
     menerima
    0.44
     eseguire
    0.44
     taking
    0.43
     memberikan
    0.43
     menciptakan
    0.42
    Activations Density 0.096%

    No Known Activations