© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260530
    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_22_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
    ޓ
    0.45
    োল
    0.41
     crowd
    0.41
    Prin
    0.40
    amiseks
    0.39
     عليه
    0.39
    啓
    0.39
    olées
    0.38
    читься
    0.38
    asis
    0.38
    POSITIVE LOGITS
     Reload
    0.45
     Refund
    0.42
    Pref
    0.39
     Oblast
    0.39
     Loyalty
    0.39
    <unused15>
    0.38
     Ride
    0.38
    Reload
    0.38
     Refunds
    0.38
     REF
    0.38
    Activations Density 0.000%

    No Known Activations