© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2577
    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
    ս
    2.87
    𝘻
    2.83
    ட்சத்திர
    2.82
    𝘳
    2.74
     plume
    2.71
    これも
    2.69
    ᥙ
    2.45
     rebate
    2.44
    ত্ব
    2.44
    𝘮
    2.40
    POSITIVE LOGITS
    ă
    3.03
    춤
    2.75
    なります
    2.72
    =\"
    2.71
    um
    2.61
    }})$
    2.60
    ness
    2.42
    다면
    2.40
    なっている
    2.39
     eher
    2.36
    Activations Density 0.012%

    No Known Activations