© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165457
    Prev
    Next
    INDEX
    Explanations

    multi-stage, multi-select, multi-head

    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_31_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
    zeb
    0.37
     Lassen
    0.37
     heo
    0.37
    ἢ
    0.36
     adaptador
    0.36
    adam
    0.34
    複数の
    0.34
     adaptor
    0.33
    BlackElo
    0.33
    这对
    0.33
    POSITIVE LOGITS
     soil
    0.40
     tranquila
    0.39
     Soil
    0.38
    土壤
    0.38
    Soil
    0.38
    bble
    0.37
     โรง
    0.37
    桩
    0.37
     rhizosphere
    0.36
     Boiler
    0.36
    Activations Density 0.002%

    No Known Activations