© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    focus on instructions

    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
     leaning
    0.74
     пона
    0.64
     никогда
    0.62
    ා
    0.62
     如
    0.61
     allemaal
    0.60
    ்
    0.60
    த்தில்
    0.59
    isArray
    0.59
     सारे
    0.59
    POSITIVE LOGITS
    t
    0.72
    ท์
    0.68
    tela
    0.67
    ഢ
    0.63
    elekt
    0.62
    いますが
    0.62
    delà
    0.61
    ה
    0.61
    tive
    0.60
    dì
    0.60
    Activations Density 0.285%

    No Known Activations