© 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. 215678
    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
     انٹر
    0.37
     positiv
    0.36
    শিক্ষ
    0.36
     Ogni
    0.36
    Meer
    0.36
     Shown
    0.36
    latt
    0.35
    㐸
    0.35
    Objective
    0.35
     pozit
    0.35
    POSITIVE LOGITS
     मिलाएं
    0.37
     gear
    0.36
     treasury
    0.36
    穰
    0.36
    ocsát
    0.35
    ：「
    0.34
     sample
    0.34
     apartheid
    0.34
    的基础
    0.34
    anaconda
    0.34
    Activations Density 0.000%

    No Known Activations