© 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. 3725
    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
    お
    1.60
    ل
    1.30
    w
    1.25
    𝕖
    1.24
    қ
    1.22
    չ
    1.18
    ι
    1.14
     تك
    1.13
    ை
    1.11
    ้
    1.09
    POSITIVE LOGITS
    )\|_{
    1.34
    ]),
    1.21
    তম
    1.16
     conjunction
    1.15
    \|^{
    1.14
    ifstream
    1.12
    lbs
    1.12
    螂
    1.11
    GameObject
    1.10
    ]++;
    1.10
    Activations Density 0.007%

    No Known Activations