© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4643
    Prev
    Next
    INDEX
    Explanations

    underline or line

    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
    સ
    2.61
    नपुर
    2.35
     mitad
    2.32
    يا
    2.31
     occhi
    2.28
    ்
    2.26
    ра
    2.26
    ଣ
    2.26
    et
    2.22
     cửa
    2.22
    POSITIVE LOGITS
    ع
    2.50
    }$)
    2.35
    ात
    2.32
    داری
    2.32
     implicitly
    2.28
     napkins
    2.28
    }'.
    2.25
    ير
    2.24
    dogs
    2.23
     MTS
    2.20
    Activations Density 0.023%

    No Known Activations