© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168941
    Prev
    Next
    INDEX
    Explanations

    0

    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_56_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
    )+\
    0.42
    лис
    0.36
    ...+
    0.35
    最近
    0.35
     সম্প্রতি
    0.35
     квартиру
    0.35
    зви
    0.34
    unehm
    0.34
     +\
    0.33
     recente
    0.33
    POSITIVE LOGITS
     fore
    0.86
     Fore
    0.80
    Fore
    0.75
     forward
    0.68
     FORE
    0.68
     Forward
    0.66
    fore
    0.62
    Forward
    0.57
    FORE
    0.55
     foreclosure
    0.54
    Activations Density 0.000%

    No Known Activations