© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216406
    Prev
    Next
    INDEX
    Explanations

    direction words

    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_31_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
     trees
    0.53
     arbres
    0.51
     tree
    0.50
     Trees
    0.50
    树
    0.49
    樹
    0.48
     Tree
    0.47
     árvore
    0.47
     나무
    0.46
     arbre
    0.46
    POSITIVE LOGITS
     земель
    0.44
    嗑
    0.42
     рабо
    0.40
     კან
    0.39
     недо
    0.38
    hob
    0.38
    佃
    0.38
     содержимое
    0.37
     કરતા
    0.37
    stedt
    0.37
    Activations Density 0.012%

    No Known Activations