© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131178
    Prev
    Next
    INDEX
    Explanations

    I am not the appropriate

    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_25_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
     déten
    0.37
    ління
    0.36
     patronage
    0.35
    Metric
    0.35
     excesses
    0.35
    텀
    0.35
     เห็น
    0.34
    滥
    0.34
    玷
    0.34
     chutney
    0.33
    POSITIVE LOGITS
    eta
    0.48
     sigue
    0.46
     состоит
    0.44
     resembles
    0.41
     encuentra
    0.39
    verbs
    0.39
     está
    0.39
    ima
    0.38
     hacia
    0.38
     पुन्हा
    0.38
    Activations Density 0.005%

    No Known Activations