© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166889
    Prev
    Next
    INDEX
    Explanations

    micro

    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_56_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
    ☻
    0.43
    áis
    0.41
     elect
    0.40
    nalia
    0.37
     पाच
    0.37
    -/-
    0.36
    INGO
    0.36
    otech
    0.36
    važ
    0.35
    宒
    0.35
    POSITIVE LOGITS
     composed
    0.45
     Compose
    0.45
     composição
    0.43
    composable
    0.43
     composé
    0.43
     composición
    0.42
     kompon
    0.42
     компози
    0.42
     compos
    0.42
    Compose
    0.42
    Activations Density 0.001%

    No Known Activations