© 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. 1811
    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
    ва
    3.22
     вот
    3.11
    И
    2.43
    }?
    2.43
     وج
    2.42
     packed
    2.37
    м
    2.36
    }}(
    2.28
    //{
    2.28
    atud
    2.28
    POSITIVE LOGITS
    jenigen
    3.18
    d
    3.03
    tı
    2.94
    اً
    2.93
    ról
    2.72
     fudai
    2.71
    datum
    2.70
    sudo
    2.70
    rafpunkte
    2.61
    ار
    2.59
    Activations Density 0.062%

    No Known Activations