© 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. 2404
    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
    ின்
    1.15
     możli
    1.14
    ни
    1.13
    њем
    1.10
    et
    1.10
    ه
    1.09
    áveis
    1.07
    andte
    1.06
    ์
    1.04
    تف
    1.04
    POSITIVE LOGITS
    𝑏
    1.38
    ১
    1.27
    𝑉
    1.14
     supernatants
    1.10
    𝑚
    1.09
    𝐾
    1.07
    𝑅
    1.05
    𝐿
    1.04
    ories
    1.02
    𝑣
    1.01
    Activations Density 0.047%

    No Known Activations