© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80346
    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_31_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
    去了
    0.45
     Ugar
    0.38
     assure
    0.38
     hanging
    0.37
     assurance
    0.36
     hang
    0.36
    去
    0.36
     promise
    0.35
     ಒ
    0.35
     assures
    0.35
    POSITIVE LOGITS
    myd
    0.36
    Paper
    0.35
    ори
    0.35
     Redistributions
    0.35
    kraft
    0.35
    ாலின்
    0.35
    raiz
    0.34
    aplik
    0.34
    ką
    0.34
    ležit
    0.33
    Activations Density 0.000%

    No Known Activations