© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2689
    Prev
    Next
    INDEX
    Explanations

    ENGINE =

    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_39_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
     didSet
    0.46
     pril
    0.38
    fieldName
    0.38
    ㇁
    0.37
    Dev
    0.36
    듕
    0.36
    udev
    0.36
    ७
    0.36
     extrap
    0.35
     pitanje
    0.35
    POSITIVE LOGITS
     relayed
    0.40
     entropy
    0.38
    Entropy
    0.37
     Neuron
    0.37
     Axi
    0.35
     দুর্
    0.35
    лас
    0.35
    র্কে
    0.35
     becoming
    0.34
     organized
    0.34
    Activations Density 0.004%

    No Known Activations