© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107831
    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_1_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
     encont
    1.12
     entreg
    1.09
    嶆
    1.09
     apreciar
    1.09
     entrevist
    1.06
     apreci
    1.05
    夎
    1.05
    н
    1.05
    ن
    1.05
     comporta
    1.03
    POSITIVE LOGITS
    3
    1.69
    7
    1.48
    9
    1.41
    1
    1.41
    2
    1.41
    6
    1.39
    8
    1.30
    5
    1.19
    ed
    1.14
    la
    1.10
    Activations Density 0.000%

    No Known Activations