© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44319
    Prev
    Next
    INDEX
    Explanations

    sun-drenched, reverb-drenched, treacherous mire

    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_13_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
     dificultades
    0.41
    ്യാപ
    0.40
     האי
    0.39
    煖
    0.39
     renormal
    0.38
    KeepOriginal
    0.38
     fissures
    0.38
     השי
    0.38
     Sebuah
    0.38
     algunas
    0.37
    POSITIVE LOGITS
    u
    0.54
    v
    0.49
    ilir
    0.47
     S
    0.44
    ro
    0.44
    at
    0.43
    ert
    0.43
    lo
    0.43
    ili
    0.43
    j
    0.43
    Activations Density 0.001%

    No Known Activations