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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257424
    Prev
    Next
    INDEX
    Explanations

    applicant's

    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_10_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
    鍥
    1.26
    Ꮄ
    1.24
    만에
    1.21
     hjust
    1.19
    라마
    1.17
    廡
    1.17
     confluent
    1.16
     jdk
    1.15
    ʢ
    1.15
     kyll
    1.15
    POSITIVE LOGITS
    len
    1.06
     deter
    0.99
    ter
    0.98
     andare
    0.95
    estrut
    0.93
     armor
    0.93
    tere
    0.93
    ల్‌
    0.93
     এছাড়াও
    0.92
     barriers
    0.91
    Activations Density 0.000%

    No Known Activations