© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107175
    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
     for
    1.96
     from
    1.59
     of
    1.58
    '
    1.44
     at
    1.34
    ে
    1.32
     with
    1.27
    ली
    1.16
    </h2>
    1.15
    </h1>
    1.13
    POSITIVE LOGITS
    ק
    1.21
    ین
    1.16
    ac
    1.16
     ஆண்டுகளாக
    1.06
    اب
    1.05
    ках
    1.02
    ويه
    0.99
    他
    0.98
    و
    0.95
    ینگ
    0.93
    Activations Density 0.000%

    No Known Activations