© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32502
    Prev
    Next
    INDEX
    Explanations

    effective/actual

    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
     Progn
    0.35
    newpage
    0.35
    เวล
    0.34
    iren
    0.34
    probable
    0.34
     confluent
    0.34
    idelberg
    0.33
    ])
    0.33
     ').
    0.33
    impulan
    0.32
    POSITIVE LOGITS
    Equality
    0.42
     freedom
    0.39
     estime
    0.38
    Kh
    0.36
     liberty
    0.35
     مدى
    0.35
     സ്വാതന്ത്ര
    0.34
    त
    0.34
    設
    0.34
     equality
    0.34
    Activations Density 0.002%

    No Known Activations