© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199762
    Prev
    Next
    INDEX
    Explanations

    voltage drop

    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_15_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
    捗
    0.17
    ﻲ
    0.16
     inspections
    0.16
    קי
    0.16
    评
    0.16
    䜣
    0.16
     मृतकों
    0.15
    Ttest
    0.15
    ”。
    0.15
    kiy
    0.15
    POSITIVE LOGITS
    ând
    0.20
     Sér
    0.19
     (&
    0.18
     trazer
    0.18
     ('
    0.18
     doar
    0.18
     Barbie
    0.18
     CSF
    0.17
     LEGO
    0.17
     wept
    0.17
    Activations Density 0.001%

    No Known Activations