© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142717
    Prev
    Next
    INDEX
    Explanations

    hashtags

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    সাং
    0.43
    journal
    0.38
    रासायनिक
    0.36
    isDisabled
    0.36
    ہا
    0.36
    誠
    0.36
     seamen
    0.35
     Yoruba
    0.35
     Gujarati
    0.35
    depression
    0.35
    POSITIVE LOGITS
     chase
    0.48
     chasing
    0.45
     chased
    0.43
     chases
    0.43
    CacheV
    0.42
     travel
    0.42
    Travel
    0.42
    追
    0.42
     viajes
    0.40
    Computation
    0.40
    Activations Density 0.002%

    No Known Activations