© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179351
    Prev
    Next
    INDEX
    Explanations

    words ending "ero"

    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
    alla
    0.49
    PIA
    0.49
    ORIA
    0.48
     आर्यन
    0.46
    рия
    0.46
     bia
    0.43
    bia
    0.42
    阶
    0.40
    oria
    0.40
     Rusia
    0.39
    POSITIVE LOGITS
    ero
    0.64
    eros
    0.54
    era
    0.53
    Merr
    0.53
    ERO
    0.52
    jero
    0.52
    mero
    0.51
     Merit
    0.50
     ero
    0.50
     era
    0.48
    Activations Density 0.001%

    No Known Activations