© 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. 133277
    Prev
    Next
    INDEX
    Explanations

    plants and trees botanical

    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
    ૄ
    0.43
     cheer
    0.42
     cim
    0.41
     rij
    0.40
    rime
    0.39
    reek
    0.38
    него
    0.38
     HEK
    0.38
    Diego
    0.38
    𐰣
    0.37
    POSITIVE LOGITS
     Peach
    0.48
    Peach
    0.42
     P
    0.42
    ান্ড
    0.41
    P
    0.39
     Allan
    0.39
     Jem
    0.39
     Wat
    0.38
     tw
    0.38
     Hamm
    0.37
    Activations Density 0.011%

    No Known Activations