© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199874
    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_46_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
    ورد
    0.38
     السيارات
    0.38
     Bootstrap
    0.38
     επισ
    0.37
    oded
    0.37
     mathsize
    0.36
    暘
    0.36
    燐
    0.35
    kir
    0.35
    イール
    0.35
    POSITIVE LOGITS
     ankle
    0.46
    century
    0.43
     unaccount
    0.42
     রোহ
    0.42
     Rohit
    0.41
    istar
    0.40
    }"),
    0.40
    },
    0.40
     movement
    0.40
    Rob
    0.39
    Activations Density 0.000%

    No Known Activations