© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13865
    Prev
    Next
    INDEX
    Explanations

    mirroring the turmoil in your own heart""crocodiles once inhabited""Mirror""mirrors""crocodiles"

    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_13_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
    ↵
    0.23
    2
    0.17
     take
    0.17
     den
    0.17
     have
    0.16
     dello
    0.16
    5
    0.16
    ly
    0.16
    \
    0.16
    ↵↵
    0.16
    POSITIVE LOGITS
    更大的
    0.17
     Caed
    0.17
    ാര്‍
    0.17
    UnityEngine
    0.16
    tsó
    0.16
    TIMEOUT
    0.16
    琚
    0.16
    ాలపై
    0.16
    ारस
    0.16
    DebuggerNonUser
    0.16
    Activations Density 0.002%

    No Known Activations