© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12727
    Prev
    Next
    INDEX
    Explanations

    random walk, angels, energy release

    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_40_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
     invariance
    0.37
    Invariant
    0.35
     culminates
    0.35
     Mum
    0.35
    Mum
    0.35
    哥
    0.35
     AppModule
    0.34
    䨪
    0.34
    amilton
    0.33
    FIL
    0.33
    POSITIVE LOGITS
     All
    0.48
     αρκε
    0.39
     modality
    0.38
     ट्रायल
    0.38
     trial
    0.38
     Trial
    0.38
     ráp
    0.36
     subsidi
    0.35
     ऑल
    0.35
     all
    0.35
    Activations Density 0.044%

    No Known Activations