© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52551
    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
    pyrazine
    0.44
    stun
    0.37
    ibar
    0.37
     isothermal
    0.37
    eren
    0.36
     countermeasures
    0.36
    （
    0.36
     metab
    0.35
    צב
    0.35
     BAI
    0.35
    POSITIVE LOGITS
    恸
    0.39
    rón
    0.38
    畱
    0.38
     ໜອງ
    0.38
    getUsername
    0.37
     Đình
    0.37
     getUsers
    0.36
     COND
    0.35
    COND
    0.35
     ફરિયાદ
    0.35
    Activations Density 0.000%

    No Known Activations