© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52674
    Prev
    Next
    INDEX
    Explanations

    allow, do, prepare

    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_30_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
    ResBuffer
    0.38
     youll
    0.38
    മുണ്ട്
    0.36
    MessageNow
    0.36
     wouldnt
    0.36
    𝙢
    0.35
     یاد
    0.35
    ਦ
    0.35
    𝙋
    0.35
    你會
    0.35
    POSITIVE LOGITS
     become
    0.47
    icherry
    0.42
     tenga
    0.40
     tengan
    0.39
     illa
    0.39
     იყოს
    0.39
     Communication
    0.38
    icale
    0.38
     provide
    0.38
     contribute
    0.38
    Activations Density 0.011%

    No Known Activations