© 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. 2900
    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
    waiting
    1.06
    eous
    1.05
    ಗಾರ
    1.00
    ी
    0.98
    ுங்கள்
    0.97
    gels
    0.96
    ták
    0.95
    と感じ
    0.95
    ு
    0.94
    touches
    0.94
    POSITIVE LOGITS
    னர்
    1.01
     meisten
    0.91
    ент
    0.88
    গতকাল
    0.87
    üst
    0.84
     fleste
    0.84
    つまり
    0.83
    तला
    0.82
    따
    0.82
     almo
    0.81
    Activations Density 0.120%

    No Known Activations