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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_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
     Utilisez
    0.37
    지금
    0.36
    Asimismo
    0.34
    t
    0.33
     ME
    0.33
    ">>
    0.32
    ін
    0.32
    ap
    0.32
    лама
    0.32
     немає
    0.32
    POSITIVE LOGITS
    spersed
    0.43
     discontent
    0.41
     تیار
    0.40
     котором
    0.39
     schizophren
    0.39
    ّى
    0.38
     контро
    0.38
    )}]
    0.38
    ங்கில
    0.38
    clad
    0.37
    Activations Density 0.000%

    No Known Activations