© 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-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178787
    Prev
    Next
    INDEX
    Explanations

    van

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     abiotic
    0.42
    ייש
    0.38
     yielded
    0.38
    Avro
    0.38
    进步
    0.37
    BURSE
    0.36
    ierno
    0.36
     추
    0.36
    랄
    0.36
     dod
    0.36
    POSITIVE LOGITS
     van
    0.49
    van
    0.49
    VAN
    0.45
     Van
    0.44
    aya
    0.43
    يا
    0.43
     GMT
    0.42
    Van
    0.41
    GMT
    0.41
    yao
    0.40
    Activations Density 0.002%

    No Known Activations