© 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. 5835
    Prev
    Next
    INDEX
    Explanations

    sensory descriptors

    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
    й
    0.60
    ی
    0.58
    睑
    0.58
    स्ट्रेट
    0.58
     dose
    0.57
    岄
    0.56
    ție
    0.56
    ဍ
    0.55
     området
    0.55
    ţie
    0.55
    POSITIVE LOGITS
    ism
    0.59
    weds
    0.55
    ல்
    0.52
    Sick
    0.52
    curr
    0.51
    tan
    0.50
    sigh
    0.50
    ರ
    0.50
    K
    0.47
     wondered
    0.47
    Activations Density 1.004%

    No Known Activations