© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34376
    Prev
    Next
    INDEX
    Explanations

    altitude and mountains

    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_50_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
    0.79
     par
    0.66
     П
    0.64
     Пар
    0.61
     پار
    0.60
     PAR
    0.58
     Parsons
    0.54
     Par
    0.53
     Parl
    0.53
    par
    0.52
    POSITIVE LOGITS
    chit
    0.44
    ਚ
    0.42
     Chir
    0.40
    NV
    0.40
    چا
    0.40
    chi
    0.38
    CHI
    0.38
    ابی
    0.38
    chim
    0.38
    LV
    0.38
    Activations Density 0.001%

    No Known Activations