© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129550
    Prev
    Next
    INDEX
    Explanations

    post-apocalyptic

    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_6_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
    ات
    1.02
    म
    1.01
    i
    0.96
    ла
    0.94
    ið
    0.93
    ды
    0.89
    대
    0.88
    지
    0.87
    nements
    0.86
    ка
    0.85
    POSITIVE LOGITS
     It
    1.38
    </h3>
    0.88
    </a>
    0.84
     politique
    0.84
     pression
    0.82
     pokrač
    0.82
     says
    0.80
    </b>
    0.79
     had
    0.79
    <td>
    0.78
    Activations Density 0.000%

    No Known Activations