© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1450
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ent
    3.20
    ب
    3.18
    на
    2.88
    ق
    2.80
     previsto
    2.76
    an
    2.76
    доб
    2.72
    on
    2.63
    بق
    2.59
    ه
    2.49
    POSITIVE LOGITS
     уж
    3.62
    ти
    3.03
    ռ
    3.00
     able
    2.99
    ها
    2.98
    ি
    2.97
    >>
    2.74
     whol
    2.72
    로
    2.72
    ING
    2.70
    Activations Density 0.022%

    No Known Activations