© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196530
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    Callories
    0.35
    如同
    0.33
    ᐋ
    0.32
    ండోత్సర్గము
    0.32
    ໋
    0.32
    োয়ার
    0.32
    ూరు
    0.32
     INDIRECT
    0.32
    ítmény
    0.31
     stojí
    0.31
    POSITIVE LOGITS
     Virginia
    0.35
     kaj
    0.33
    据
    0.33
     Pilot
    0.32
    url
    0.32
    pilot
    0.32
    %,
    0.32
    km
    0.31
     authentic
    0.30
    mer
    0.30
    Activations Density 0.000%

    No Known Activations