© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85761
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
    识
    0.50
    ölker
    0.50
    kező
    0.47
     Слу
    0.46
    illés
    0.46
     Затем
    0.45
     జన్
    0.45
     Харків
    0.44
    legel
    0.44
    水口
    0.44
    POSITIVE LOGITS
    electrical
    0.55
    وڑا
    0.54
    ک
    0.53
    سی
    0.52
    サ
    0.52
     electrical
    0.51
    امہ
    0.50
    𝑠
    0.49
    ہ
    0.49
    کار
    0.49
    Activations Density 0.000%

    No Known Activations