© 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. 3399
    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
    ো
    3.21
    𝐞
    2.73
    다고
    2.58
    ang
    2.44
    滘
    2.35
    ্সের
    2.34
    હ
    2.32
    ți
    2.31
    ಶಸ್
    2.27
    𝐚
    2.26
    POSITIVE LOGITS
    क
    2.27
    ৪৩
    2.22
    voor
    2.20
    ﺀ
    2.20
    ৪০
    2.16
    ء
    2.14
     altro
    2.13
     Calle
    2.07
    руппа
    2.04
     UGC
    2.03
    Activations Density 0.032%

    No Known Activations