© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2905
    Prev
    Next
    INDEX
    Explanations

    text, model, definition, or question

    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_5_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
    𝙨
    0.27
     casualties
    0.27
     craters
    0.25
    ️⃣
    0.25
     militants
    0.25
    bhp
    0.25
    ⃣
    0.25
     arguably
    0.25
     ਇਸ
    0.25
     recesses
    0.24
    POSITIVE LOGITS
    gir
    0.24
     misma
    0.22
    getDay
    0.22
    ظمة
    0.21
     anden
    0.21
    g
    0.21
     hará
    0.21
    evil
    0.21
     Đặc
    0.20
     také
    0.20
    Activations Density 1.864%

    No Known Activations