© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244338
    Prev
    Next
    INDEX
    Explanations

    Path Get

    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_40_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
     Marcel
    0.40
    system
    0.39
    र्तन
    0.38
    NSMakeRange
    0.38
    systems
    0.37
    ྕ
    0.37
     system
    0.37
    StubCompat
    0.37
     सुरंग
    0.37
     Bhojpuri
    0.37
    POSITIVE LOGITS
    iedz
    0.39
    OHN
    0.38
    elligent
    0.37
    莆
    0.37
    ListIterator
    0.37
    usal
    0.36
     gouttes
    0.36
     बढ़ा
    0.36
     solu
    0.35
    Solutions
    0.35
    Activations Density 0.000%

    No Known Activations