© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    because he

    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
    д
    1.17
    urn
    1.11
    MPa
    1.10
    ኼ
    1.09
    and
    1.09
     desp
    1.09
    द
    1.04
    {
    1.03
     totality
    1.02
     prognosis
    1.02
    POSITIVE LOGITS
    ទ្
    1.44
    rauen
    1.44
    CHREIB
    1.44
    soever
    1.39
    मण
    1.38
    此之外
    1.36
    ន្ទ
    1.36
    nae
    1.34
    циа
    1.33
    ICAGO
    1.33
    Activations Density 0.002%

    No Known Activations