© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69691
    Prev
    Next
    INDEX
    Explanations

    short vowel sounds

    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
    inse
    0.37
    mal
    0.36
    ctive
    0.36
    swering
    0.35
    olem
    0.34
    谦
    0.34
     informational
    0.34
    wed
    0.34
    器材
    0.33
    蛔
    0.33
    POSITIVE LOGITS
    eh
    0.45
    ej
    0.43
     ईरानी
    0.40
    eeee
    0.40
    ead
    0.39
    াকারী
    0.39
    evol
    0.38
     Cib
    0.37
    Lookup
    0.37
    ee
    0.37
    Activations Density 0.024%

    No Known Activations