© 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. 60113
    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
    6
    1.43
    1
    1.36
    8
    1.32
    5
    1.05
    ای
    1.05
    UN
    1.03
    ]
    1.02
    7
    1.02
     is
    1.00
     of
    0.98
    POSITIVE LOGITS
    in
    1.16
    າ
    1.01
    ၊
    0.98
    ب
    0.98
    ら
    0.96
    𝐞
    0.93
    ാ
    0.92
    व
    0.92
    し
    0.92
    ק
    0.91
    Activations Density 0.000%

    No Known Activations