© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235340
    Prev
    Next
    INDEX
    Explanations

    tunneling tracker

    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_46_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
     P
    0.53
    P
    0.51
     karbon
    0.41
    孚
    0.40
     isoform
    0.38
    buah
    0.38
    П
    0.37
    Carbon
    0.36
    zyma
    0.36
     p
    0.36
    POSITIVE LOGITS
     dct
    0.42
     lic
    0.41
     শিশ
    0.40
     IDX
    0.39
     Bali
    0.39
    lici
    0.38
    gcj
    0.38
    肚
    0.38
     पुरी
    0.37
    एसएल
    0.37
    Activations Density 0.006%

    No Known Activations