© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160352
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ير
    1.30
    <td>
    1.04
    ो
    1.00
    0.99
     I
    0.92
    8
    0.91
     Deps
    0.90
    <0x0D>
    0.89
     neke
    0.89
    2
    0.88
    POSITIVE LOGITS
    ด
    1.58
    د
    1.38
    ก
    1.27
    та
    1.25
    त
    1.18
    ac
    1.17
    of
    1.17
    ท
    1.16
    ک
    1.12
    c
    1.09
    Activations Density 0.000%

    No Known Activations