© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228570
    Prev
    Next
    INDEX
    Explanations

    maximum or more

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     hipot
    0.42
    露
    0.41
    orden
    0.37
     neuronal
    0.36
    loon
    0.36
     سات
    0.36
     practicing
    0.35
    atorul
    0.35
     gen
    0.34
     Suck
    0.34
    POSITIVE LOGITS
     má
    1.17
     ма
    0.78
    má
    0.77
    Má
    0.64
     Má
    0.61
    ма
    0.49
     마
    0.48
    마
    0.48
     mend
    0.42
     merges
    0.41
    Activations Density 0.001%

    No Known Activations