© 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. 2670
    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
    sulfanyl
    2.65
    ل
    2.61
     अगु
    2.22
    जिला
    2.18
    撾
    2.14
     sponge
    2.11
     awali
    2.10
     inaction
    2.10
    <unused1111>
    2.09
     allegiance
    2.06
    POSITIVE LOGITS
    そのまま
    2.59
     Câmara
    2.46
    ্রে
    2.40
    as
    2.36
    ка
    2.34
    𝒕
    2.31
    ة
    2.22
    ного
    2.21
     halide
    2.14
     espera
    2.12
    Activations Density 0.039%

    No Known Activations