© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15964
    Prev
    Next
    INDEX
    Explanations

    The presence of `+` and `@@` in `MAX_ACTIVATING_TOKENS`, combined with tokens like `1`, `ous`, and `hetically` in `TOKENS_AFTER_MAX_ACTIVATING_TOKEN`, suggests a pattern related to code or differential text.```textdiff hunk markers```

    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_15_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
    r
    0.67
    is
    0.60
    ing
    0.58
    ers
    0.55
    es
    0.53
    s
    0.53
    ન
    0.53
    erk
    0.52
    en
    0.52
    ens
    0.49
    POSITIVE LOGITS
    ксана
    0.56
     deuterium
    0.54
     )-
    0.54
     कंडक्टर
    0.54
     नाइट्रोजन
    0.53
     +(
    0.52
     lze
    0.52
    ቃል
    0.52
    氮
    0.52
    нее
    0.51
    Activations Density 0.000%

    No Known Activations