© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126090
    Prev
    Next
    INDEX
    Explanations

    leaves and plant descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    蕁
    0.43
    泫
    0.40
     libraries
    0.39
    खों
    0.38
     инфраструк
    0.38
     MST
    0.37
    บอล
    0.37
     BE
    0.36
     fuertes
    0.36
     Athe
    0.36
    POSITIVE LOGITS
     wedge
    0.71
    wedge
    0.67
    ∧
    0.65
    Wed
    0.64
     Wedge
    0.64
     Wed
    0.61
     wed
    0.59
     wedges
    0.59
    WED
    0.47
    楔
    0.47
    Activations Density 0.011%

    No Known Activations