© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196759
    Prev
    Next
    INDEX
    Explanations

    food combinations

    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
     steve
    0.42
     zej
    0.41
     Zr
    0.40
     emote
    0.38
    Steve
    0.38
    沒
    0.38
    酩
    0.37
     STE
    0.37
     größte
    0.37
     addict
    0.37
    POSITIVE LOGITS
     Jamie
    0.38
     মধ
    0.38
    ꯔ
    0.37
    utt
    0.36
     Прав
    0.36
    Jamie
    0.36
    ࿔
    0.35
    ាស
    0.35
     odb
    0.35
    <unused33>
    0.34
    Activations Density 0.004%

    No Known Activations