© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4686
    Prev
    Next
    INDEX
    Explanations

    "it takes courage to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ت
    2.06
    leş
    1.85
    ‌ನ
    1.69
     tandem
    1.58
    ଈ
    1.51
    ઓની
    1.51
     Hoc
    1.50
    تال
    1.50
    ఞ
    1.50
     trivalent
    1.50
    POSITIVE LOGITS
    к
    1.48
    ில்
    1.43
    ion
    1.16
    and
    1.14
    й
    1.14
    ू
    1.10
    োগ
    1.10
    க்கும்
    1.09
    ne
    1.09
    MB
    1.08
    Activations Density 0.180%

    No Known Activations