© 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. 206328
    Prev
    Next
    INDEX
    Explanations

    written narrative

    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
    getBase
    0.40
    పోయింది
    0.37
    俱
    0.34
    Speech
    0.33
     কণ্ঠ
    0.32
    gutter
    0.31
    parat
    0.31
     bomba
    0.31
    વેશ
    0.31
     機
    0.31
    POSITIVE LOGITS
     write
    1.89
    写
    1.76
     writing
    1.73
     kirjo
    1.73
     escrever
    1.69
    write
    1.66
    寫
    1.65
     escribir
    1.64
     Write
    1.63
     scrivere
    1.63
    Activations Density 0.072%

    No Known Activations