© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7382
    Prev
    Next
    INDEX
    Explanations

    LLaMA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
    дә
    1.51
    彡
    1.34
     стоковое
    1.33
    𝙩
    1.30
     불구
    1.29
    жидан
    1.28
     существуют
    1.27
     света
    1.26
     αφού
    1.22
    続きを読む
    1.20
    POSITIVE LOGITS
    ب
    1.61
    ر
    1.54
    al
    1.48
    𝐞
    1.43
     retrouve
    1.40
    рда
    1.38
    eer
    1.33
    ם
    1.32
    те
    1.31
    ঞ্জেল
    1.31
    Activations Density 0.007%

    No Known Activations