© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3681
    Prev
    Next
    INDEX
    Explanations

    question words

    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
    ्स
    2.60
    ્સ
    2.23
    ्सा
    2.08
    ̗
    2.05
     wavelengths
    1.97
    >.</
    1.97
    s
    1.96
     caudal
    1.91
    யின்
    1.90
    lah
    1.90
    POSITIVE LOGITS
    rst
    2.32
    الت
    2.10
     свойств
    2.10
    ચર
    2.05
    𝔯
    2.04
     nito
    2.02
     efectivos
    2.01
    ของการ
    2.00
     مما
    1.99
     роста
    1.98
    Activations Density 0.000%

    No Known Activations