© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215673
    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_5_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
    י
    1.44
    。
    1.35
    지
    1.30
    レ
    1.30
    ล
    1.24
    ।
    1.22
    ロ
    1.19
    ル
    1.18
    ي
    1.16
    ד
    1.13
    POSITIVE LOGITS
    '
    1.74
    is
    1.54
    _
    1.31
    s
    1.30
    €™
    1.22
    ’
    1.21
    r
    1.16
    at
    1.15
    ní
    1.09
    ine
    1.07
    Activations Density 0.000%

    No Known Activations