© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68143
    Prev
    Next
    INDEX
    Explanations

    "Mel" or "El"

    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_51_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
     Ul
    0.44
     Angeb
    0.43
    PAF
    0.40
    估
    0.39
     ul
    0.38
    Ul
    0.38
    ulty
    0.38
    eterm
    0.37
     Avan
    0.37
    rendo
    0.36
    POSITIVE LOGITS
    el
    0.73
    ελ
    0.70
    엘
    0.64
     Mel
    0.64
    Mel
    0.64
    EL
    0.63
     mel
    0.61
    elio
    0.61
    mel
    0.60
    MEL
    0.59
    Activations Density 0.015%

    No Known Activations