© 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. 200881
    Prev
    Next
    INDEX
    Explanations

    plant species

    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
     conval
    0.46
     sinter
    0.40
     tray
    0.39
    볐
    0.38
     mic
    0.37
    เส
    0.37
     Soph
    0.37
     terrib
    0.36
    جے
    0.36
     riforma
    0.36
    POSITIVE LOGITS
    CS
    0.42
    ყ
    0.41
     PDT
    0.40
     yattha
    0.39
     Daddy
    0.39
    ാത്ത
    0.38
    Coat
    0.38
    zigzag
    0.37
    巴巴
    0.36
     খাদ্য
    0.36
    Activations Density 0.000%

    No Known Activations