© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122983
    Prev
    Next
    INDEX
    Explanations

    living standards

    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_3_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
     actifs
    0.96
     allongé
    0.86
    ある
    0.84
     objectifs
    0.83
     கூடிய
    0.80
     azienda
    0.80
    쐞
    0.80
     Fonbet
    0.79
     caoutch
    0.79
     comenc
    0.79
    POSITIVE LOGITS
    :
    1.20
    '
    1.13
     I
    1.08
    ’
    1.08
    ong
    1.02
    )
    0.92
    it
    0.91
    "
    0.90
    are
    0.88
    Living
    0.86
    Activations Density 0.001%

    No Known Activations