© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32781
    Prev
    Next
    INDEX
    Explanations

    position/direction

    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_50_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
     온
    0.36
    issant
    0.36
    OG
    0.34
    ysl
    0.34
     얼마
    0.34
     ON
    0.33
    ..”
    0.33
    滄
    0.33
     Bs
    0.32
    라마
    0.32
    POSITIVE LOGITS
     aside
    0.49
    Upon
    0.46
     upon
    0.46
     forth
    0.46
    aside
    0.46
    forth
    0.45
     Upon
    0.44
    besides
    0.44
     besides
    0.42
    Ago
    0.40
    Activations Density 0.315%

    No Known Activations